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. 35923
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
     barrels
    -0.08
    _puts
    -0.08
     labels
    -0.07
    pare
    -0.07
     جميع
    -0.07
    Duplicate
    -0.07
     whale
    -0.07
     contiene
    -0.07
    知识产权
    -0.07
     unter
    -0.07
    POSITIVE LOGITS
    具体情况
    0.08
    反过来
    0.07
    要么
    0.07
    istor
    0.07
    _NOTIFICATION
    0.07
    enk
    0.07
    怎么做
    0.07
    裙子
    0.07
    שק
    0.07
    _PARAMS
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.