© 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. 35-TRANSCODER-HP
    7. 39575
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chef
    -0.28
    award
    -0.28
    äºĨä¸Ģ
    -0.27
    zcze
    -0.27
    adays
    -0.26
     award
    -0.26
    coach
    -0.25
    ²
    -0.25
     Award
    -0.25
    '+
    -0.25
    POSITIVE LOGITS
    åĽ¹
    0.27
    ProgressDialog
    0.25
    ListComponent
    0.25
    ouro
    0.25
    ä¸ĢåĪĨéĴ±
    0.24
    /OR
    0.24
    äºĮ线åŁİå¸Ĥ
    0.24
     bulk
    0.24
    URT
    0.24
    æij©
    0.24
    Activations Density 3.380%

    No Known Activations

    This feature has no known activations.