© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 150622
    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
    aData
    -0.27
     Aero
    -0.27
     ÑģебÑı
    -0.26
     Middle
    -0.26
     Audi
    -0.26
    boarding
    -0.25
     boarding
    -0.25
    boat
    -0.24
    ocked
    -0.24
     filler
    -0.24
    POSITIVE LOGITS
    ç§Ģ
    0.28
    ä¸ĭè¾¾
    0.27
    VENT
    0.26
    hus
    0.26
    ä¼łæī¿
    0.25
    éĹ¯
    0.25
    ãĢĨ
    0.24
    绣
    0.23
    phas
    0.23
     crossorigin
    0.23
    Activations Density 0.115%

    No Known Activations

    This feature has no known activations.