© 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. 39579
    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
    bral
    -0.29
     ministers
    -0.26
     Sinn
    -0.25
    KH
    -0.24
     complexion
    -0.24
    们
    -0.24
    KI
    -0.24
     Highlander
    -0.23
    RY
    -0.23
     basal
    -0.23
    POSITIVE LOGITS
    -fix
    0.28
    angkan
    0.27
    -depend
    0.26
    -pill
    0.26
     ALIGN
    0.26
    vect
    0.25
    bic
    0.25
    -grow
    0.25
    å®ŀæĸ½æĦıè§ģ
    0.25
    -package
    0.24
    Activations Density 17.631%

    No Known Activations

    This feature has no known activations.