© 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. 140909
    Prev
    Next
    INDEX
    Explanations

    common words

    np_max-act · gemini-2.0-flash
    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
    éĶļ
    -0.28
    WithPath
    -0.28
    åģı
    -0.27
    è¯Ŀé¢ĺ
    -0.25
    obia
    -0.25
    Bias
    -0.24
     immer
    -0.24
     bırak
    -0.24
    editable
    -0.24
    inder
    -0.23
    POSITIVE LOGITS
     smooth
    0.28
     harmless
    0.27
     Smooth
    0.27
    gor
    0.27
     Nor
    0.26
    smooth
    0.26
    âĢ¢
    0.26
     ...(
    0.26
     sins
    0.25
     Honest
    0.25
    Activations Density 5.729%

    No Known Activations