© 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. 31997
    Prev
    Next
    INDEX
    Explanations

    theory tracking type

    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
     appunto
    -0.08
    meer
    -0.08
    #.
    -0.07
    æ²Ľ
    -0.07
    å§Ĩæĸ¯
    -0.07
     importantly
    -0.07
    "..
    -0.07
    ШÐĺ
    -0.07
    #__
    -0.07
    享
    -0.07
    POSITIVE LOGITS
    æĪĸèĢħæĺ¯
    0.10
    æĪĸèĢħåħ¶ä»ĸ
    0.09
    æĪĸèĢħæľī
    0.09
    æĪĸæĺ¯
    0.08
    以åıĬåIJĦç§į
    0.08
     dó
    0.08
    ä¹ĭç±»çļĦ
    0.07
    ney
    0.07
    æĪĸçĶ¨
    0.07
    åĴĮåIJĦç§į
    0.07
    Activations Density 0.518%

    No Known Activations