© 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. 149877
    Prev
    Next
    INDEX
    Explanations

    Âł

    np_max-act-logits · gemini-2.0-flash
    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
    ä¸ĢæľŁ
    -0.30
    æ·ł
    -0.27
    è¿ĻéĩĮæĺ¯
    -0.27
    -required
    -0.26
    zá
    -0.25
    ä¸Ģè§Ī
    -0.25
    antino
    -0.25
    æĸ°éĹ»ç½ij
    -0.24
     Installer
    -0.24
    æĮīæŶ
    -0.24
    POSITIVE LOGITS
    avior
    0.28
     thirds
    0.27
    itage
    0.25
    Bottom
    0.25
    æĿĤ
    0.25
     Socialist
    0.25
     Historic
    0.24
     newItem
    0.24
    boot
    0.24
    èIJĮ
    0.24
    Activations Density 0.127%

    No Known Activations