© 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. 27612
    Prev
    Next
    INDEX
    Explanations

    sophisticated

    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
    å®īåħ¨è´£ä»»
    -0.08
    ä¸įå¼ĥ
    -0.08
    ä¸Ģä¸Ŀ
    -0.08
    åĺ¶
    -0.07
    ings
    -0.07
    ford
    -0.07
    ä¸ĢåŃĹ
    -0.07
    umah
    -0.07
    æĪij们ä¼ļ尽快
    -0.07
    ilog
    -0.06
    POSITIVE LOGITS
     enough
    0.07
    IRST
    0.07
    imizer
    0.07
    ÑĢалÑĮ
    0.07
    PLEX
    0.07
     ast
    0.07
    ally
    0.07
    ÙĪس
    0.07
    REEN
    0.07
    ìĻķ
    0.07
    Activations Density 0.003%

    No Known Activations