© 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. 24-TRANSCODER-HP
    7. 151221
    Prev
    Next
    INDEX
    Explanations

    Code and website parsing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĪ»
    -0.24
    é¦ĸåħĪ
    -0.24
    urt
    -0.23
    vation
    -0.23
    åĪ»çĶ»
    -0.23
    OMP
    -0.23
     Martial
    -0.23
     kÃŃch
    -0.23
     vision
    -0.23
     TURN
    -0.23
    POSITIVE LOGITS
    [assembly
    0.29
    çľģæĶ¿åºľ
    0.28
    çĽ¡
    0.27
    illin
    0.26
    .nb
    0.25
    nb
    0.25
    amble
    0.25
    秣éĩij
    0.24
    è¸Į
    0.24
    enco
    0.24
    Activations Density 0.049%

    No Known Activations