© 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. 28871
    Prev
    Next
    INDEX
    Explanations

    something else

    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
    sumer
    -0.08
    راÙģÙĤ
    -0.08
    swith
    -0.08
    æĢ§åľ°
    -0.08
    éĺħ读åİŁæĸĩ
    -0.08
    æĿ¥å¾ĹåıĬ
    -0.08
    ÅĻÃŃzenÃŃ
    -0.08
    lesi
    -0.07
    ucer
    -0.07
    ================================================================
    -0.07
    POSITIVE LOGITS
    Ùĩ
    0.11
    u
    0.09
    Ñĥ
    0.08
    ed
    0.08
    ãĥ³
    0.08
    ת
    0.08
    ToMany
    0.08
    ãĢħãģ®
    0.08
    ie
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    Activations Density 0.027%

    No Known Activations