© 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. 27-TRANSCODER-HP
    7. 57422
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¹ĸåĮº
    -0.28
     #{@
    -0.27
    dk
    -0.26
    ewan
    -0.25
    INLINE
    -0.25
     Straight
    -0.24
     measure
    -0.24
    ãĥ§
    -0.24
    ={[
    -0.23
     malformed
    -0.23
    POSITIVE LOGITS
    populate
    0.30
    æĿ¾å¼Ľ
    0.28
    pret
    0.26
     XK
    0.26
    actors
    0.25
    å¸¦ä½ł
    0.25
    wand
    0.25
    owoÅĽci
    0.25
    大æĸ¹
    0.25
     harb
    0.25
    Activations Density 0.882%

    No Known Activations

    This feature has no known activations.