© 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. 142671
    Prev
    Next
    INDEX
    Explanations

    binary and bits

    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
    Negative Logits
    裱
    -0.31
    -radius
    -0.26
    yii
    -0.25
     repost
    -0.25
     полÑĥ
    -0.24
    bard
    -0.24
     dood
    -0.24
     measurements
    -0.24
     solids
    -0.24
    ä¼°
    -0.24
    POSITIVE LOGITS
    andscape
    0.31
    binary
    0.31
     binary
    0.30
     bitwise
    0.30
    ä½İä½į
    0.29
    -hot
    0.29
    .binary
    0.28
    æĻ¯
    0.27
    (binary
    0.26
    .Binary
    0.25
    Activations Density 13.987%

    No Known Activations