© 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. 24-TRANSCODER-HP
    7. 149466
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dess
    -0.28
    ÑĨев
    -0.28
    æĬĬæīĭ
    -0.27
    ubby
    -0.26
    广åijĬæľįåĬ¡
    -0.25
    healthy
    -0.25
    æĥ³èµ·äºĨ
    -0.25
     tus
    -0.24
     healthy
    -0.24
     pumping
    -0.24
    POSITIVE LOGITS
    ä»ĵ
    0.27
    èį£å¹¸
    0.27
    à¸ķร
    0.24
    âĺħâĺħ
    0.24
     Reign
    0.24
    çķĻä¸ĭæĿ¥
    0.23
    Cod
    0.23
    interpre
    0.23
     Five
    0.23
    Four
    0.23
    Activations Density 1.075%

    No Known Activations

    This feature has no known activations.