© 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. 39996
    Prev
    Next
    INDEX
    Explanations

    web frameworks and code structure

    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
    affer
    -0.07
    æ³ķå¾ĭè§Ħå®ļ
    -0.07
     dep
    -0.07
    ä¸Ńåŀĭ
    -0.07
    ByName
    -0.06
     подви
    -0.06
    å¹´å·¥ä½ľ
    -0.06
    киÑı
    -0.06
    kala
    -0.06
    åIJIJ
    -0.06
    POSITIVE LOGITS
    åİŁæĸĩéĵ¾æİ¥
    0.07
    åħ¬åı·
    0.07
    æľ¬æĸĩ为
    0.07
    è¦ģæ±Ĥè¿Ľè¡Į
    0.07
    =yes
    0.06
    _ignore
    0.06
     Schlag
    0.06
    _restore
    0.06
    evole
    0.06
     versehen
    0.06
    Activations Density 0.497%

    No Known Activations