© 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. 27-TRANSCODER-HP
    7. 7661
    Prev
    Next
    INDEX
    Explanations

    CHRIST

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ipient
    -0.28
    quets
    -0.27
    ogn
    -0.26
    à°Ĺ
    -0.26
    iterate
    -0.26
    charge
    -0.25
    ominated
    -0.25
    ÙĤد
    -0.25
    ä¸Ģä½ĵ
    -0.25
    .gnu
    -0.25
    POSITIVE LOGITS
    Va
    0.28
     deal
    0.27
     Accom
    0.25
    æľĪä¸Ń
    0.25
    bk
    0.25
     vac
    0.25
    rsp
    0.24
     Vac
    0.24
    %"↵
    0.24
    ulfill
    0.24
    Activations Density 0.002%

    No Known Activations