© 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. 18430
    Prev
    Next
    INDEX
    Explanations

    values, rates, results, content

    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
    ä¸¥æł¼è¦ģæ±Ĥ
    -0.07
    าà¸ĩ
    -0.07
     diger
    -0.07
    åıªæľīèĩªå·±
    -0.07
    æĹłå¤Ħ
    -0.07
     strictly
    -0.07
     grow
    -0.07
    详ç»ĨäºĨ解
    -0.07
     Jus
    -0.06
    é¦ĸåħĪåľ¨
    -0.06
    POSITIVE LOGITS
    à¸Ńม
    0.09
    æİ¥è¿ij
    0.08
    amber
    0.08
    èm
    0.08
    è¿Ļä¸İ
    0.07
    è¶ħ人
    0.07
    åĨįçİ°
    0.07
    符åIJĪ
    0.07
    à¹ĥà¸ģลà¹īà¹Ģà¸Ħียà¸ĩ
    0.07
    åĨįçı¾
    0.07
    Activations Density 0.021%

    No Known Activations