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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 109137
    Prev
    Next
    INDEX
    Explanations

    Filepaths, teams, organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Body
    -0.30
    çļĦè´¨éĩı
    -0.28
     body
    -0.27
    \Schema
    -0.26
    éļİ
    -0.26
    两端
    -0.26
    lin
    -0.26
    æ±°
    -0.25
    ä½ĵ
    -0.25
    è´¨éĩı管çIJĨ
    -0.25
    POSITIVE LOGITS
    etu
    0.31
     fruits
    0.29
     Leg
    0.28
     fruit
    0.28
    fruit
    0.28
    æ°´æŀľ
    0.25
    ruit
    0.25
    èĴĤ
    0.25
    ruits
    0.25
     extra
    0.25
    Activations Density 0.904%

    No Known Activations