© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26923
    Prev
    Next
    INDEX
    Explanations

    Karnofsky, SR, cis, explot, fluor, cort, Ad, beta

    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
    orsa
    -0.07
    æĶ¾çĶŁ
    -0.07
    æĶ¯ä»ĺæĸ¹å¼ı
    -0.06
     bucks
    -0.06
     matters
    -0.06
    è¿Ħ
    -0.06
    ass
    -0.06
     QUAN
    -0.06
     eid
    -0.06
    ä¹ĺ
    -0.05
    POSITIVE LOGITS
    ç±»åĴĮ
    0.08
    çī©è¯Ń
    0.08
     %+
    0.08
    &T
    0.07
    °
    0.07
    ç»ıæµİè´¸æĺĵ
    0.07
    为代表çļĦ
    0.07
    è¡ĮéĹ´
    0.07
    (),'
    0.07
     Salut
    0.07
    Activations Density 0.065%

    No Known Activations