© 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. 31281
    Prev
    Next
    INDEX
    Explanations

    summary:

    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
    osl
    -0.08
     '::
    -0.07
    /////
    -0.07
    .sl
    -0.07
    Ñİза
    -0.07
    adou
    -0.07
    Canonical
    -0.07
    мелÑĮ
    -0.07
    为èį£
    -0.06
    acol
    -0.06
    POSITIVE LOGITS
    asser
    0.08
    å¾Īæĺİæĺ¾
    0.07
    _VO
    0.07
    æĺ¾çĦ¶
    0.07
    æ¯ķ
    0.07
    Aws
    0.07
    ä¸Ģå¾ĭ
    0.07
    ç»ĵ论
    0.06
    ipper
    0.06
    ç®Ģæĺĵç¨ĭåºı
    0.06
    Activations Density 0.140%

    No Known Activations