© 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. 150084
    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
    è¿Ļå¼ł
    -0.27
    ä¸ĭ游
    -0.27
     Investing
    -0.26
    obile
    -0.25
    çļĦæĬķèµĦ
    -0.24
     amph
    -0.24
    ï¬ĥ
    -0.24
     Manual
    -0.24
     hon
    -0.23
    manual
    -0.23
    POSITIVE LOGITS
    ilar
    0.26
    vasion
    0.25
    éĻ¢
    0.25
    ao
    0.24
    ongan
    0.24
    pra
    0.24
    ilee
    0.24
    åķĨ
    0.24
     ila
    0.24
    ighted
    0.23
    Activations Density 0.181%

    No Known Activations

    This feature has no known activations.