© 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. 56020
    Prev
    Next
    INDEX
    Explanations

    dextrous Rama, wondrous body, stick, uniforms

    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
    褪
    -0.07
    ç§Ĵ
    -0.07
    ä¸ĸç´Ģ
    -0.07
    äºľ
    -0.07
     Hog
    -0.07
    æĤĦ
    -0.07
    Ĥ
    -0.06
    è¶Ł
    -0.06
     slag
    -0.06
    æŁ¥æŁ¥
    -0.06
    POSITIVE LOGITS
    åħŃç§į
    0.09
    æ¸ħåĩĢ
    0.09
    äºĶç§į
    0.09
    ä½ıå¤Ħ
    0.08
    ondrous
    0.08
    æ¯Ķä¸ĺ
    0.08
    åĽĽé¡¹
    0.08
    orer
    0.08
    ä¸īéŨ
    0.08
    abh
    0.08
    Activations Density 0.005%

    No Known Activations