© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56971
    Prev
    Next
    INDEX
    Explanations

    code elements and keywords

    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
    ajs
    -0.07
    润泽
    -0.06
     Tat
    -0.06
    chter
    -0.06
    dale
    -0.06
    heed
    -0.06
    çĻ½éĵ¶
    -0.06
    nton
    -0.06
    asting
    -0.06
     |
    -0.06
    POSITIVE LOGITS
    ges
    0.08
    "."
    0.08
    [,
    0.07
    èĩªå·±éĥ½
    0.07
    ç»ıæľ¬éĻ¢
    0.07
    izr
    0.07
    æīĢå±ŀåĪĨç±»
    0.07
    ,proto
    0.07
    ä½ľä¸ºä¸Ģ项
    0.07
    ãģ«ä¿Ĥ
    0.07
    Activations Density 0.186%

    No Known Activations