© 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. 34422
    Prev
    Next
    INDEX
    Explanations

    original or translation

    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
    人éĹ´
    -0.07
    ób
    -0.07
    holt
    -0.07
    æ·¡
    -0.06
    第ä¸īæī¹
    -0.06
    даÑĢ
    -0.06
    ä½ı
    -0.06
     Bangsa
    -0.06
    ptime
    -0.06
    odb
    -0.06
    POSITIVE LOGITS
    ä¹°ä¹°
    0.09
    ä¸Ń磩
    0.08
    izr
    0.08
    }while
    0.07
    erialize
    0.07
    uldig
    0.07
    .Navigation
    0.07
     SER
    0.07
    åĪĨ享åĪ°
    0.07
    ohlen
    0.07
    Activations Density 0.001%

    No Known Activations