© 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. 19366
    Prev
    Next
    INDEX
    Explanations

    scientific or technical paper citations

    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
    å§Ĩæĸ¯
    -0.07
    kad
    -0.07
    åİŁä½ľèĢħ
    -0.07
    iedere
    -0.07
     original
    -0.06
    åİŁæľī
    -0.06
    éĿĻéĿĻ
    -0.06
    aired
    -0.06
    alai
    -0.06
    é¦ĸéĥ¨
    -0.06
    POSITIVE LOGITS
    ignées
    0.07
    ä¸Ģçķª
    0.07
     rigorous
    0.07
    zz
    0.07
    zerw
    0.07
    å¾Ģå¤ĸ
    0.07
    .TypeOf
    0.06
    å¢ŀåĩı
    0.06
    äºĶè¡Įå±ŀ
    0.06
    nds
    0.06
    Activations Density 0.012%

    No Known Activations