© 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. 22090
    Prev
    Next
    INDEX
    Explanations

    actions involving preparation and use

    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°±æĺ¯ä½łçļĦ
    -0.07
    ä¸ĢåIJij
    -0.06
    ç®Ģ书
    -0.06
    idd
    -0.06
    ÅĤady
    -0.06
    argas
    -0.06
    èħ¾èħ¾
    -0.06
    ponent
    -0.06
    ä¹ĭå®Ŀ
    -0.06
    åĵģçļĦ
    -0.06
    POSITIVE LOGITS
    åĴĮ使çĶ¨
    0.09
    åıĬ使çĶ¨
    0.08
    ocs
    0.08
    /type
    0.08
    /use
    0.07
    µ
    0.07
    /manage
    0.07
    è¿ĩä¸Ģ次
    0.07
    èĭijå°ıåĮº
    0.07
    æĪĸ使çĶ¨
    0.07
    Activations Density 0.442%

    No Known Activations