© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9119
    Prev
    Next
    INDEX
    Explanations

    Fourth Court of Appeals

    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
    æĬĦ
    -0.07
    èĭ«
    -0.06
    ToEnd
    -0.06
    绩
    -0.06
    irm
    -0.06
    çīĩçīĩ
    -0.06
    IZZ
    -0.06
    orno
    -0.06
    avÃŃa
    -0.06
    å¦ĤåĽł
    -0.06
    POSITIVE LOGITS
    oproject
    0.07
    á»ķ
    0.07
    utch
    0.07
    æIJŀå®ļ
    0.07
     scrut
    0.07
    æĺ¯åIJ¦èĥ½å¤Ł
    0.07
    bern
    0.06
     cá»Ĺ
    0.06
    ×Ļ×ķ
    0.06
    éĥ¨éķ¿
    0.06
    Activations Density 0.003%

    No Known Activations