© 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. 8083
    Prev
    Next
    INDEX
    Explanations

    whose

    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
    éĺĸ
    -0.07
     بÙĪدÙĨ
    -0.07
    ä¸Ģ个éĩįè¦ģ
    -0.07
    à¹Ģà¸Ľà¹ĩà¸Ļà¸ģาร
    -0.07
    æĭīåħĭ
    -0.07
    çļĦæĺ¯ä¸Ģ个
    -0.07
    uess
    -0.07
    å§ĭèĩ³
    -0.06
    ì²´ìĿ¸
    -0.06
    rira
    -0.06
    POSITIVE LOGITS
     whose
    0.15
    whose
    0.12
     cuya
    0.10
     cuyo
    0.10
     cuyos
    0.09
     cujo
    0.09
     cuja
    0.09
     that
    0.09
     اÙĦتÙĬ
    0.08
     with
    0.08
    Activations Density 0.226%

    No Known Activations