© 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. 8826
    Prev
    Next
    INDEX
    Explanations

    why, how, that

    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
     originals
    -0.08
    беÑĤ
    -0.08
    ä¹Łç¡®å®ŀ
    -0.08
    irks
    -0.08
    ç¡®æľī
    -0.07
    czyn
    -0.07
    ossal
    -0.07
    ä¹Łå¤ļ
    -0.07
    иÑİ
    -0.07
    ignet
    -0.07
    POSITIVE LOGITS
    åijĹ
    0.08
     Weih
    0.07
    æĩ¿
    0.07
    åįľ
    0.07
    èĥĮæĻ¯ä¸ĭ
    0.06
    æľīåħ³äºİ
    0.06
    çķ
    0.06
    æ³ģ
    0.06
    à¦ģ
    0.06
    ä¸įèĥľ
    0.06
    Activations Density 0.023%

    No Known Activations