© 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. 106907
    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
     particle
    -0.29
    åŃļ
    -0.27
    WO
    -0.27
    å¿ĥä¸Ń
    -0.26
    //(
    -0.26
    particle
    -0.26
    æijĨåľ¨
    -0.26
    celed
    -0.25
    HN
    -0.25
    çŃł
    -0.25
    POSITIVE LOGITS
    =res
    0.28
     theaters
    0.27
    ensored
    0.27
    åĽ½åľŁ
    0.26
    abler
    0.25
    ables
    0.25
    =f
    0.24
    _reservation
    0.24
    鼷æĸ¯
    0.24
    ForResource
    0.23
    Activations Density 34.292%

    No Known Activations

    This feature has no known activations.