© 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. 15626
    Prev
    Next
    INDEX
    Explanations

    makeshift conditions, scarcity, violence

    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
     underrated
    -0.09
    人ä¹ĭ
    -0.08
    rypton
    -0.08
    æŁIJ人
    -0.07
     Slut
    -0.07
    åĪijäºĭæĭĺçķĻ
    -0.07
    æŃ¥è¡Įè¡Ĺ
    -0.07
    æŁĶç¾İ
    -0.07
    ä¼ļè®®ä¸Ńå¿ĥ
    -0.07
    åľ¨ä¸Ģå®ļ
    -0.07
    POSITIVE LOGITS
     makeshift
    0.09
    æł¹æľ¬æĹłæ³ķ
    0.08
    ç®Ģæĺĵ
    0.08
    è·¯éĢı
    0.08
    æľĢåŁºæľ¬çļĦ
    0.08
     rud
    0.08
     confiscated
    0.08
    æĹłæ³ķæŃ£å¸¸
    0.08
     sic
    0.07
     improvised
    0.07
    Activations Density 0.205%

    No Known Activations