© 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. 62106
    Prev
    Next
    INDEX
    Explanations

    qualities and abilities

    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
    èĩªå·±æĥ³è¦ģ
    -0.07
    adin
    -0.07
    ä¸įæ²»
    -0.07
    iations
    -0.07
    brig
    -0.07
    tk
    -0.07
    Úĺ
    -0.07
    NotFoundException
    -0.07
    TEMPL
    -0.07
    æĺ¥æļĸ
    -0.06
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.11
    ability
    0.11
     ìŬë¶Ģ
    0.11
    ity
    0.11
    ness
    0.11
     ìŬë¶Ģ를
    0.10
    åIJ¦
    0.10
    fulness
    0.10
    leness
    0.10
    ноÑģÑĤÑĮ
    0.09
    Activations Density 0.205%

    No Known Activations