© 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. 31922
    Prev
    Next
    INDEX
    Explanations

    json processing

    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
    æĽĿ
    -0.07
    á»ıi
    -0.07
    jav
    -0.07
    é¾ĻæĹı
    -0.07
    oport
    -0.07
    ]%
    -0.07
    人æĹı
    -0.07
    次äºİ
    -0.07
    饥饿
    -0.07
    raj
    -0.07
    POSITIVE LOGITS
    soon
    0.07
    ures
    0.07
    alts
    0.07
    è¡ĮåĬ¨è®¡åĪĴ
    0.07
    åıĪåĥı
    0.07
    era
    0.06
    éĽ£
    0.06
    ä¸įæ²»
    0.06
    param
    0.06
    ä¸įäºĨäºĨ
    0.06
    Activations Density 0.002%

    No Known Activations