© 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. 44890
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

    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
     Gutsche
    -0.09
    ka
    -0.07
    aset
    -0.07
    пей
    -0.07
    acher
    -0.07
    erton
    -0.07
    ạch
    -0.07
    åŃ¢
    -0.07
    ahi
    -0.07
    çī©ç¾İ
    -0.07
    POSITIVE LOGITS
    LogLevel
    0.06
    ffin
    0.06
    æĪij以åIJİ
    0.06
    å¼Ģå§ĭåľ¨
    0.06
    ä»ĸå¼Ģå§ĭ
    0.06
    é§
    0.06
    inj
    0.06
     inj
    0.06
    说好
    0.06
    æŃ¥å±¥
    0.06
    Activations Density 0.002%

    No Known Activations