© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 34704
    Prev
    Next
    INDEX
    Explanations

    suicide prevention resources

    np_max-act · gemini-2.0-flash

    mentions of suicidal ideation, self-harm, or crisis help and the assistant's safety/support responses (hotlines, urging to seek help).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Formation
    -0.07
    Timeline
    -0.07
    TAB
    -0.07
     turnovers
    -0.07
    🕋
    -0.07
    addin
    -0.07
    _FM
    -0.07
     anlaşma
    -0.07
     menstr
    -0.07
    而这
    -0.07
    POSITIVE LOGITS
    (Long
    0.08
    探
    0.07
    .getLongitude
    0.07
    轴
    0.07
    游
    0.07
    (&
    0.07
     neuken
    0.07
     {↵↵
    0.07
    復
    0.07
    目
    0.07
    Activations Density 0.095%

    No Known Activations