© 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. 58116
    Prev
    Next
    INDEX
    Explanations

    graph properties and problems

    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
    å±ĬæŶ
    -0.08
    çĪ¶çĪ±
    -0.08
     Float
    -0.07
     Garn
    -0.07
    isode
    -0.07
    主ä½ĵå·¥ç¨ĭ
    -0.07
    åIJĦçݯèĬĤ
    -0.07
    Float
    -0.07
    zeti
    -0.07
    reb
    -0.07
    POSITIVE LOGITS
     mutual
    0.10
    Mut
    0.08
    eran
    0.08
    mut
    0.07
    å½¼æѤ
    0.07
    _mut
    0.07
    社交
    0.07
     Mutual
    0.07
    æ¸Ĭ
    0.07
    äºĴ缸
    0.07
    Activations Density 0.007%

    No Known Activations