© 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. 40275
    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
    راÙĩ
    -0.28
    份
    -0.26
     BCH
    -0.26
    uis
    -0.25
     repmat
    -0.25
    åıĸå¾Ĺ
    -0.24
    icides
    -0.24
    aghetti
    -0.24
    lations
    -0.24
    ARS
    -0.23
    POSITIVE LOGITS
     convers
    0.27
     Disc
    0.25
     sprink
    0.25
     orth
    0.24
     importance
    0.24
     Owned
    0.24
     dish
    0.24
    fa
    0.24
     spo
    0.23
     Dish
    0.23
    Activations Density 1.011%

    No Known Activations

    This feature has no known activations.