© 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. 41445
    Prev
    Next
    INDEX
    Explanations

    .react, .func, analysis

    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
    .offsetTop
    -0.08
     CONCE
    -0.07
    _literals
    -0.07
    æīĵè¿ĩ
    -0.07
    çģµå±±
    -0.07
    èĥĮæĻ¯å¢Ļ
    -0.07
    PackageManager
    -0.07
    æĶ¶æĭ¾
    -0.07
    衬æīĺ
    -0.07
    angga
    -0.07
    POSITIVE LOGITS
    çĶ¨æĪ·åı¯ä»¥éĢļè¿ĩ
    0.08
    oud
    0.07
    çĶ¨æĪ·æıIJä¾Ľ
    0.07
    çĶ¨æĪ·åı¯ä»¥
    0.07
    çĶ¨æĪ·ä¸Ĭä¼ł
    0.06
    èĥľä»»
    0.06
     users
    0.06
    人社
    0.06
    ubb
    0.06
    å°¼æĸ¯
    0.06
    Activations Density 0.432%

    No Known Activations