© 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. 49319
    Prev
    Next
    INDEX
    Explanations

    unusual characters

    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
    ç¼ĺæķħ
    -0.08
    åįĥåįĥ
    -0.06
    åįĥåįĥä¸ĩ
    -0.06
    á»įn
    -0.06
    anim
    -0.06
    ana
    -0.06
    inters
    -0.06
    inster
    -0.06
     Khá»iji
    -0.06
     block
    -0.06
    POSITIVE LOGITS
    bras
    0.09
    ctor
    0.08
    бÑĢÑı
    0.08
    ifa
    0.07
    è±ģ
    0.07
    å¼łçİī
    0.07
    æıIJé«ĺèĩªèº«
    0.07
    ä¸Ĭè¿Ľå¿ĥ
    0.07
    åIJĵå¾Ĺ
    0.07
    моÑĤ
    0.07
    Activations Density 0.001%

    No Known Activations