© 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. 24258
    Prev
    Next
    INDEX
    Explanations

    related to scientific findings

    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
     szok
    -0.08
    Ùģت
    -0.07
    大大å°ıå°ıçļĦ
    -0.07
    缴æİ¥æĪĸéĹ´æİ¥
    -0.07
    ðŁ
    -0.07
    åıĺå¾Ĺè¶ĬæĿ¥è¶Ĭ
    -0.07
    (that
    -0.07
    agul
    -0.07
    è¿Ļä¸ĢåĿĹ
    -0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.07
    POSITIVE LOGITS
    [J
    0.08
    %C
    0.07
    .pdf
    0.07
    -role
    0.07
    ãĢİ
    0.07
     ‘
    0.07
    Äħtek
    0.07
    AndUpdate
    0.06
    —an
    0.06
    åıĬ缸åħ³
    0.06
    Activations Density 1.128%

    No Known Activations