© 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. 50605
    Prev
    Next
    INDEX
    Explanations

    measurement parameters and values

    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
    "]->
    -0.07
    à¸Ĺีà¹Īมีà¸Ħวาม
    -0.07
    ä½ľä¸ºä¸Ģç§į
    -0.07
    æĮºå¥½
    -0.07
    æľīæķĪçļĦ
    -0.07
    ç®Ĺæĺ¯
    -0.07
     Undert
    -0.07
    æĪĸ许æľī
    -0.07
    ä¹ĭå¤Ħåľ¨äºİ
    -0.06
    criptors
    -0.06
    POSITIVE LOGITS
    rey
    0.08
    çŃīäºİ
    0.07
    æĺ¯å¤ļå°ij
    0.07
    å®ļæł¼
    0.07
    ames
    0.07
     equals
    0.07
    éļıé£İ
    0.06
    è·Łèĩªå·±
    0.06
    åĽ½å®¶ç¨İåĬ¡æĢ»å±Ģ
    0.06
    æľĽè¿ľ
    0.06
    Activations Density 0.024%

    No Known Activations