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. 59711
    Prev
    Next
    INDEX
    Explanations

    changed

    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
     BitmapFactory
    -0.08
    Vel
    -0.07
    ۼ
    -0.07
    _page
    -0.07
     북
    -0.07
    莫名其
    -0.07
     textSize
    -0.07
     עקב
    -0.07
     tinha
    -0.07
    芴
    -0.07
    POSITIVE LOGITS
    _dependency
    0.08
     weren
    0.08
     po
    0.08
     �
    0.08
     Irr
    0.07
    主題
    0.07
     Master
    0.07
     intersection
    0.07
    iss
    0.07
    exists
    0.07
    Activations Density 0.019%

    No Known Activations