© 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. 1814
    Prev
    Next
    INDEX
    Explanations

    links and code snippets

    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
    <|box_end|>
    -0.14
    erior
    -0.11
    Ø©
    -0.11
    ä¸įç´Ĭ
    -0.11
    agher
    -0.11
    并èĮĤ
    -0.10
    apy
    -0.10
    uvre
    -0.10
    ytter
    -0.10
    ä¿±è¿Ľ
    -0.10
    POSITIVE LOGITS
    ä¸įåı¯æĢĿè®®
    0.21
    身临åħ¶å¢ĥ
    0.20
    äºĭåįĬåĬŁåĢį
    0.17
    åĭĩå¾Ģ缴åīį
    0.17
    åħ¨å¿ĥåħ¨æĦı
    0.16
    åħ¢åħ¢ä¸ļä¸ļ
    0.15
    两åѦä¸Ģåģļ
    0.14
    缸è¾ħ缸æĪIJ
    0.13
    ä¼ĹæīĢåij¨çŁ¥
    0.13
    èĢ³çĨŁèĥ½è¯¦
    0.13
    Activations Density 0.016%

    No Known Activations