© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 131144
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     using
    -0.26
     Scholars
    -0.25
     posed
    -0.24
    using
    -0.24
    è¯·ä½ł
    -0.24
    åIJ¸
    -0.24
    Paren
    -0.24
     Chancellor
    -0.24
    long
    -0.23
    éri
    -0.23
    POSITIVE LOGITS
    çĨŁ
    0.31
    bler
    0.30
     vej
    0.26
    ’in
    0.26
     finely
    0.25
    .createFrom
    0.25
    vero
    0.25
    âĹģ
    0.24
    htag
    0.24
     tug
    0.24
    Activations Density 29.279%

    No Known Activations

    This feature has no known activations.