© 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. 60994
    Prev
    Next
    INDEX
    Explanations

    construction components

    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
     Vic
    -0.06
    粧
    -0.06
    nyi
    -0.06
    åľ¨ä½ı
    -0.06
    °
    -0.06
    Vic
    -0.06
    izar
    -0.06
     VIC
    -0.06
    KOM
    -0.06
    çģ°å¿ĥ
    -0.06
    POSITIVE LOGITS
    itect
    0.09
    bart
    0.08
    å°Ķé¡¿
    0.07
    alow
    0.07
    inos
    0.07
    /latest
    0.07
    缴
    0.07
    ãĥŃãĥĬ
    0.07
    以å¤ĸçļĦ
    0.07
    ä¹Łä¸įä¾ĭå¤ĸ
    0.07
    Activations Density 0.049%

    No Known Activations