© 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. 35-TRANSCODER-HP
    7. 38846
    Prev
    Next
    INDEX
    Explanations

    project

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     clums
    -0.32
     humour
    -0.32
     idiots
    -0.31
     pl
    -0.30
     faults
    -0.29
     misses
    -0.29
     hell
    -0.29
     cheeks
    -0.29
     humor
    -0.28
     crud
    -0.28
    POSITIVE LOGITS
    TÃľ
    0.28
     Nagar
    0.26
     APK
    0.25
     DOJ
    0.25
     TILE
    0.25
    (GET
    0.25
     GPI
    0.25
    ITH
    0.25
    [MAXN
    0.24
     GetString
    0.24
    Activations Density 6.039%

    No Known Activations