© 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. 38887
    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
     organisation
    -0.30
    cker
    -0.27
    åħĭæĢĿ
    -0.27
    prox
    -0.26
    ackage
    -0.26
    flix
    -0.24
    -pointer
    -0.24
    lops
    -0.24
    ilee
    -0.24
    kp
    -0.24
    POSITIVE LOGITS
    å¸Ĥå§Ķ书记
    0.25
    æĬµ
    0.25
    å±İ
    0.24
    åݻ买
    0.24
    chu
    0.24
    çªľ
    0.24
    头ä¸Ĭ
    0.23
    é¼»
    0.23
    æįĤ
    0.23
    å£ģ
    0.23
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.