© 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. 49569
    Prev
    Next
    INDEX
    Explanations

    want to / like to

    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
    转贴
    -0.08
    artet
    -0.08
    lighet
    -0.08
    менов
    -0.08
    åıij表æŶéĹ´
    -0.08
     basically
    -0.08
    Õ¡Õ°
    -0.07
    ault
    -0.07
    dra
    -0.07
    好æ¯Ķ
    -0.07
    POSITIVE LOGITS
    Ø©
    0.07
    onet
    0.07
    à¹Į
    0.06
    ä¸İéĶĢåĶ®
    0.06
    ä¹ĭ交
    0.06
    áĢº
    0.06
    иÑİ
    0.06
    è¿ĩ度çļĦ
    0.06
    ä¾ĭ
    0.06
    unya
    0.06
    Activations Density 0.031%

    No Known Activations