© 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. 129286
    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
    æīĺ
    -0.35
    æĵį
    -0.29
    shot
    -0.28
    lige
    -0.27
    tab
    -0.27
    borough
    -0.27
    tors
    -0.27
    AttributeValue
    -0.26
    举
    -0.26
     Mouth
    -0.25
    POSITIVE LOGITS
     presently
    0.27
    便æĺ¯
    0.26
    osos
    0.26
    ICC
    0.25
    -feed
    0.25
    åı±
    0.25
     entire
    0.25
    便
    0.25
    feed
    0.25
     genie
    0.24
    Activations Density 10.556%

    No Known Activations

    This feature has no known activations.