© 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. 61372
    Prev
    Next
    INDEX
    Explanations

    file extensions (.md)

    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
    _COMPILE
    -0.07
    apar
    -0.07
    ies
    -0.06
    aney
    -0.06
    anee
    -0.06
    å¦ĤåĽ¾æīĢ示
    -0.06
    atta
    -0.06
    estro
    -0.06
    å¦Ĥä¸ĭåĽ¾æīĢ示
    -0.05
    åIJįä¸ĭ
    -0.05
    POSITIVE LOGITS
    çݩ转
    0.08
     enfin
    0.08
    phu
    0.08
    æłij人
    0.07
    çĿ¹
    0.07
    æļĹå¤ľ
    0.07
    æĽĻåħī
    0.07
    ehend
    0.07
    aturi
    0.07
    æĭ©
    0.07
    Activations Density 0.102%

    No Known Activations