© 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. 18-TRANSCODER-HP
    7. 88203
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    elson
    -0.29
    hare
    -0.27
     [{"
    -0.27
    hores
    -0.27
     EXPRESS
    -0.27
    hoc
    -0.24
     RSVP
    -0.24
    ÑĪе
    -0.24
    UNK
    -0.24
    è··
    -0.24
    POSITIVE LOGITS
    _exceptions
    0.28
    rette
    0.26
    dé
    0.26
    è¿Ľ
    0.25
    @m
    0.25
    è¿ĽäºĨ
    0.25
    _except
    0.25
    +m
    0.24
    çļĦæĪIJåĬŁ
    0.24
    ana
    0.23
    Activations Density 63.861%

    No Known Activations