© 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. 61327
    Prev
    Next
    INDEX
    Explanations

    Rewrite

    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
    ımı
    -0.07
    å¦Ĥä¸Ģ
    -0.07
    ä¸ĭä¸Ģ级
    -0.06
    æŁIJ个
    -0.06
    eki
    -0.06
    ÏĩÏį
    -0.06
    ontra
    -0.06
    æľ¬ä¸ĵä¸ļ
    -0.06
    ÐĤ
    -0.06
    æĻ®
    -0.06
    POSITIVE LOGITS
    ä¿¡èµĸ
    0.09
    rik
    0.08
    é¸
    0.07
    人æĿ¥è¯´
    0.07
    oplast
    0.07
    ẹt
    0.07
    ajan
    0.07
    RIPT
    0.06
    ä¸į设
    0.06
    nak
    0.06
    Activations Density 0.002%

    No Known Activations