© 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. 34433
    Prev
    Next
    INDEX
    Explanations

    asking a question

    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
    æµ·é»ĺ
    -0.09
    еÑĤен
    -0.08
    èĮī
    -0.08
    缴æİ¥åIJij
    -0.07
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    ä¸įåĴĮ
    -0.07
     EITHER
    -0.07
    代ä¹ĭ
    -0.07
    ä¸Ģå¹´åĽĽåŃ£
    -0.07
    %x
    -0.07
    POSITIVE LOGITS
    è°ģ家
    0.07
    araf
    0.07
    éĹ»
    0.07
    è¦ģæĬĬ
    0.07
    æľįåĬ¡æľºæŀĦ
    0.07
    rit
    0.06
    ums
    0.06
     intercept
    0.06
    CCA
    0.06
    adas
    0.06
    Activations Density 0.008%

    No Known Activations