© 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. 25-TRANSCODER-HP
    7. 109500
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    xffff
    -0.25
     school
    -0.24
     finals
    -0.24
    istrator
    -0.24
    ounty
    -0.23
    åĵ©
    -0.23
    .He
    -0.23
     chóng
    -0.23
     tint
    -0.23
    _pars
    -0.23
    POSITIVE LOGITS
    achs
    0.26
    è°ĵ
    0.24
    _AA
    0.24
    åįıåĬ©
    0.24
    ami
    0.24
     awaited
    0.24
     Tablets
    0.23
    uada
    0.23
    force
    0.23
    izedName
    0.23
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.