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

    Neuronpedia

    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. 15-RESID-POST-AA
    11. 14961
    Prev
    Next
    INDEX
    Explanations

    Questioning sources/potential bias

    np_max-act · gemini-2.0-flash

    mentions of legal authority, judgment, accusations, or institutional oversight (e.g., judge/accused, appointing, policing themselves).

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    חוף
    -0.07
    uali
    -0.07
     systemic
    -0.07
    JI
    -0.07
    'We
    -0.07
    全面
    -0.07
    .and
    -0.07
    徨
    -0.07
    “
    -0.07
    mue
    -0.07
    POSITIVE LOGITS
     topo
    0.07
     Dr
    0.07
    Mgr
    0.07
     HW
    0.07
    .productId
    0.07
     locality
    0.07
    的优点
    0.06
     noticing
    0.06
    birthdate
    0.06
     Uses
    0.06
    Activations Density 0.075%

    No Known Activations