© 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. 38900
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    angers
    -0.34
    ced
    -0.30
    .Dict
    -0.25
     Sark
    -0.25
    attles
    -0.25
    æŃ¼
    -0.25
    anger
    -0.25
    ameleon
    -0.25
     past
    -0.24
    pu
    -0.24
    POSITIVE LOGITS
    computed
    0.27
    бÑĢа
    0.26
    æĬĬæīĭ
    0.24
    owy
    0.24
    balances
    0.24
    åѱ
    0.23
     tapped
    0.23
    veal
    0.23
     shaped
    0.23
     onNext
    0.23
    Activations Density 5.196%

    No Known Activations

    This feature has no known activations.