© 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. 31-TRANSCODER-HP
    7. 19696
    Prev
    Next
    INDEX
    Explanations

    ca

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    tees
    -0.35
    亲
    -0.33
    tee
    -0.30
    ees
    -0.28
    agraph
    -0.28
     col
    -0.27
    chten
    -0.26
     carr
    -0.26
     vacancy
    -0.25
    rient
    -0.25
    POSITIVE LOGITS
    æĵį纵
    0.27
     Lens
    0.25
     Kö
    0.24
    å¼Ħ
    0.24
    å®īå®ļ
    0.23
     handguns
    0.23
    _stand
    0.23
    redit
    0.23
    yo
    0.23
    static
    0.23
    Activations Density 0.887%

    No Known Activations