© 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. 28021
    Prev
    Next
    INDEX
    Explanations

    sale, purchase, or data transfer

    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
    onnier
    -0.08
    acob
    -0.07
    ä¸įæĶ¾
    -0.07
    ÙĬÙĦØ©
    -0.07
     doule
    -0.07
    Ắ
    -0.07
    icismo
    -0.07
    eszt
    -0.07
    æ²³éķĩ
    -0.07
    aille
    -0.07
    POSITIVE LOGITS
    -like
    0.08
    åĻ¨çŃī
    0.08
    èĪ¬
    0.07
    amiliar
    0.06
    ment
    0.06
    åĻ¨
    0.06
    å°±æĺ¯è¯´
    0.06
    ç±»
    0.06
    åľ°å®ĮæĪIJ
    0.06
    åĻ¨åĴĮ
    0.06
    Activations Density 0.626%

    No Known Activations