© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21044
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ìį¨
    -0.11
    uum
    -0.10
    untung
    -0.10
    ¹Ħ
    -0.10
    <|box_end|>
    -0.09
    leon
    -0.09
    dden
    -0.09
    cula
    -0.09
    ziali
    -0.09
    artment
    -0.09
    POSITIVE LOGITS
    s
    0.23
    缸è¾ħ缸æĪIJ
    0.22
    es
    0.21
    åĬłæĭ¿å¤§
    0.18
    ä¼ĹæīĢåij¨çŁ¥
    0.17
    o
    0.17
    a
    0.17
    ات
    0.17
    åĭĩå¾Ģ缴åīį
    0.16
    ä¸įåı¯æĢĿè®®
    0.16
    Activations Density 0.044%

    No Known Activations