© 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. 129512
    Prev
    Next
    INDEX
    Explanations

    Rev

    np_max-act · gemini-2.0-flash
    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
    寞
    -0.07
    救助
    -0.07
    WISE
    -0.07
    .Json
    -0.07
    .Le
    -0.07
    stable
    -0.07
    精华
    -0.07
    农业农村
    -0.06
    デン
    -0.06
    .hardware
    -0.06
    POSITIVE LOGITS
     propName
    0.07
    支配
    0.07
     Pret
    0.07
    🔚
    0.07
    Feels
    0.06
    .Float
    0.06
    副作用
    0.06
    terminal
    0.06
     Docs
    0.06
     Mog
    0.06
    Activations Density 0.000%

    No Known Activations