© 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. 39301
    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
     imagine
    -0.28
     mam
    -0.28
     maman
    -0.27
    aber
    -0.27
     ade
    -0.27
     mama
    -0.26
    aba
    -0.26
    ä¼ļä¸Ĭ
    -0.26
     mostly
    -0.26
    awa
    -0.26
    POSITIVE LOGITS
     Nd
    0.31
    æ°´
    0.30
    Nd
    0.30
    .nd
    0.29
    ndl
    0.28
     Water
    0.28
    uers
    0.28
    ND
    0.28
    yre
    0.28
    wdx
    0.27
    Activations Density 21.360%

    No Known Activations

    This feature has no known activations.