© 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. 23386
    Prev
    Next
    INDEX
    Explanations

    contains or requests illegal

    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
    æĿŃ
    -0.06
    ç±»åĪ«
    -0.06
    æİ¥
    -0.06
    åħ¬å¹³
    -0.06
     categor
    -0.06
     regard
    -0.05
    éģ
    -0.05
    ingroup
    -0.05
    istik
    -0.05
    Pas
    -0.05
    POSITIVE LOGITS
    eret
    0.08
    lds
    0.08
    ÃŃces
    0.07
    ÅĽc
    0.07
    mach
    0.07
    killer
    0.07
    ÃŃtó
    0.07
    åĬłçıŃåĬłçĤ¹
    0.07
    æłij人
    0.07
    éĹ®é¢ĺè¿Ľè¡Į
    0.07
    Activations Density 0.001%

    No Known Activations