© 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. 140895
    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
     iota
    -0.28
    令
    -0.27
     Continue
    -0.25
    æŃ»äº¡
    -0.25
    killer
    -0.25
    çļĦä¼ĺåĬ¿
    -0.25
    ç¹¼çºĮ
    -0.24
    dest
    -0.24
    _continue
    -0.24
    fty
    -0.24
    POSITIVE LOGITS
     CSP
    0.28
    çĿĢçľ¼
    0.27
     Democr
    0.27
    ensa
    0.27
    åĩºåħ¥
    0.26
    ovid
    0.26
    ·¨
    0.25
    alte
    0.24
    uÅŁ
    0.24
    æīĵæĬĺ
    0.24
    Activations Density 32.355%

    No Known Activations

    This feature has no known activations.