© 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. 30-TRANSCODER-HP
    7. 96813
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĻ
    -0.28
     sounding
    -0.26
    rog
    -0.25
     links
    -0.24
     equ
    -0.24
     over
    -0.24
     tracking
    -0.24
     tooth
    -0.24
    _String
    -0.24
    ä¸İåIJ¦
    -0.24
    POSITIVE LOGITS
     Approach
    0.29
    aison
    0.28
    å·¥ä¸ļåĮĸ
    0.27
    ourn
    0.27
     Extend
    0.26
     auss
    0.24
    PointerType
    0.24
    _step
    0.24
     pis
    0.23
    gae
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.