© 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. 108470
    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
     casts
    -0.26
    æ°¸éģł
    -0.24
    éªĪ
    -0.24
     Pods
    -0.24
    alth
    -0.23
     createAction
    -0.23
    à¦ī
    -0.23
    akest
    -0.23
    amt
    -0.23
    ."č↵
    -0.23
    POSITIVE LOGITS
     citation
    0.26
    icus
    0.26
    .nih
    0.25
    çĹħæ¯ĴæĦŁæŁĵ
    0.25
    åľ°æ¯¯
    0.25
    çļĩåĨł
    0.24
    sky
    0.24
    éĩijèŀįåį±æľº
    0.24
    insky
    0.23
    ivo
    0.23
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.