© 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. 51188
    Prev
    Next
    INDEX
    Explanations

    these or this followed by noun

    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
    æľ¬ç«ĻæīĢæľī
    -0.06
    æĺ¯èĢģ
    -0.06
     íĴĪ
    -0.06
    ì²Ļ
    -0.06
     Ic
    -0.06
    alit
    -0.06
    åĵģ
    -0.06
    ç¤
    -0.06
    -columns
    -0.06
     Stand
    -0.06
    POSITIVE LOGITS
     latter
    0.09
    eming
    0.08
     wÅĤaÅĽnie
    0.08
    insen
    0.08
    çĤ¹çĤ¹æ»´æ»´
    0.07
    çļĦè¿Ļç§į
    0.07
     блоге
    0.07
    个个
    0.07
    翼翼
    0.07
    -ever
    0.07
    Activations Density 0.196%

    No Known Activations