Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 24380
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sources
    -0.08
    ocratic
    -0.08
     observers
    -0.07
    /img
    -0.07
    .Stop
    -0.07
     Contact
    -0.06
    棕色
    -0.06
    .AddModelError
    -0.06
    一看
    -0.06
    褶
    -0.06
    POSITIVE LOGITS
     drib
    0.08
    َ
    0.07
    fte
    0.07
     adultery
    0.07
    ТЕ
    0.07
     tricky
    0.07
    	retval
    0.06
    stalk
    0.06
    _MARKER
    0.06
    OrElse
    0.06
    Activations Density 0.014%

    No Known Activations