© 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. 140928
    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
    å¦Ĥæŀľæľī
    -0.27
    %S
    -0.26
    å¦Ĥæŀľæ²¡æľī
    -0.25
    穹
    -0.24
    éĩijå¸ģ
    -0.24
    黡
    -0.24
    zÅij
    -0.24
     Cald
    -0.23
    resco
    -0.23
    -driving
    -0.23
    POSITIVE LOGITS
    åĴĮçĿ¦
    0.24
    Verified
    0.24
    åģĥ
    0.24
    âľĵ
    0.24
     convenient
    0.23
    elas
    0.23
    éĵī
    0.23
     Fest
    0.23
    Prec
    0.23
     fest
    0.23
    Activations Density 7.364%

    No Known Activations

    This feature has no known activations.