© 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. 39297
    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
    .then
    -0.27
    åĽłåŃIJ
    -0.26
    ol
    -0.26
    oms
    -0.25
     noi
    -0.25
     Rowe
    -0.25
    å¾Ĵå¼Ł
    -0.25
     alc
    -0.25
    æī£éĻ¤
    -0.25
    /thumb
    -0.25
    POSITIVE LOGITS
    ftar
    0.26
     Tam
    0.25
    ERN
    0.24
    fur
    0.24
    angel
    0.24
     Ner
    0.24
     unrestricted
    0.24
    -lib
    0.23
    .ut
    0.23
    [text
    0.23
    Activations Density 42.193%

    No Known Activations

    This feature has no known activations.