© 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. 150373
    Prev
    Next
    INDEX
    Explanations

    Anyone

    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
    è¿ĺåı¯
    -0.29
     cou
    -0.28
     coup
    -0.28
    ä¸į平衡
    -0.27
    好çļĦ
    -0.26
    lose
    -0.26
    èī¯å¥½çļĦ
    -0.25
    еÑģÑĤÑĮ
    -0.25
    ä¹Łåı¯
    -0.25
    è¿ĺåı¯ä»¥
    -0.25
    POSITIVE LOGITS
    amb
    0.30
    æĥ³
    0.28
     amb
    0.26
    füh
    0.26
    æĥ³çŁ¥éģĵ
    0.25
     inquire
    0.24
    endon
    0.24
    otent
    0.24
    amura
    0.24
    aptive
    0.24
    Activations Density 0.056%

    No Known Activations