© 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. 38939
    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
     ...,
    -0.25
     steps
    -0.25
    @return
    -0.24
    ä¸į好
    -0.24
    ;color
    -0.24
    å¦ĸ
    -0.24
    iage
    -0.24
     financ
    -0.24
    ive
    -0.23
     finding
    -0.23
    POSITIVE LOGITS
    elta
    0.27
    ầy
    0.26
    ifestyles
    0.24
    æł·å¼ı
    0.24
    arten
    0.23
    touches
    0.23
    ç²¾èĭ±
    0.23
    æĭ¦
    0.23
     Holdings
    0.23
    åķĨä¸ļ
    0.23
    Activations Density 1.696%

    No Known Activations

    This feature has no known activations.