© 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. 56392
    Prev
    Next
    INDEX
    Explanations

    overview of topics

    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
    Ỽt
    -0.08
    æĺİç¡®æıIJåĩº
    -0.08
     prem
    -0.07
    ä¸įè§ģ
    -0.07
    resh
    -0.07
    haj
    -0.07
    emo
    -0.07
     Guimarães
    -0.07
    æĸ°æĢĿè·¯
    -0.07
    éĶ¦æ¶Ľ
    -0.07
    POSITIVE LOGITS
    ç®Ģè¦ģ
    0.10
     basics
    0.09
     describing
    0.09
     overview
    0.09
    ä»ĭç»į
    0.08
     briefly
    0.08
    æ¦ĤåĨµ
    0.08
    ä»ĭç»įäºĨ
    0.08
     describe
    0.08
    涵çĽĸäºĨ
    0.08
    Activations Density 0.058%

    No Known Activations