© 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. 20-TRANSCODER-HP
    7. 64499
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sting
    -0.29
     easily
    -0.27
     further
    -0.26
     defeat
    -0.24
    .gameObject
    -0.24
     successful
    -0.23
    æĹ©æĹ©
    -0.23
    æ´²
    -0.23
     stad
    -0.23
    egen
    -0.23
    POSITIVE LOGITS
    ä¸įè´Ł
    0.27
    pare
    0.27
    天èĬ±
    0.26
    æĸ°åįİç½ij
    0.26
     AttributeSet
    0.26
    .mozilla
    0.25
    htar
    0.25
    imit
    0.24
    icers
    0.24
    sez
    0.24
    Activations Density 21.374%

    No Known Activations

    This feature has no known activations.