© 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. 25231
    Prev
    Next
    INDEX
    Explanations

    rather than, instead of

    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
    upes
    -0.07
    ulut
    -0.07
    uilt
    -0.07
    istan
    -0.07
    ä¸įæŃ¢
    -0.07
    _optimizer
    -0.07
     offs
    -0.07
    utton
    -0.07
    rome
    -0.07
     insomma
    -0.07
    POSITIVE LOGITS
    ãģĿãģĨãģ§
    0.08
    åħ¶ä»ĸæĸ¹å¼ı
    0.08
    åįķ纯çļĦ
    0.08
    åįķ纯
    0.08
    åĸ®ç´Ķ
    0.07
     other
    0.07
    hton
    0.07
    åħ¬åı¸é¢Ĩ导
    0.07
     pa
    0.06
    llib
    0.06
    Activations Density 0.159%

    No Known Activations