© 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. 43197
    Prev
    Next
    INDEX
    Explanations

    delete item

    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
    ali
    -0.07
    AHAN
    -0.07
     Nim
    -0.06
    /detail
    -0.06
    ahan
    -0.06
     detachment
    -0.06
    inkel
    -0.06
    å°½åı¯èĥ½çļĦ
    -0.06
    ALI
    -0.06
    éĹ»
    -0.06
    POSITIVE LOGITS
    creat
    0.08
    µľ
    0.08
    å¹´ä¸ĭåįĬå¹´
    0.08
    IDEO
    0.07
    åĪĽ
    0.07
    BOSE
    0.07
     finire
    0.07
    庸
    0.07
    ä»įåľ¨
    0.07
     Pek
    0.07
    Activations Density 0.147%

    No Known Activations