© 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. 1034
    Prev
    Next
    INDEX
    Explanations

    chemical formulas involving CH

    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
    igs
    -0.07
     اÙĦصØŃÙĬØŃ
    -0.06
    bara
    -0.06
    ¢
    -0.06
    æ´ģ
    -0.06
    sem
    -0.06
    åı¯æģ¶
    -0.06
    ÙĦÛĮ
    -0.06
    ä¸įçĿĢ
    -0.06
    試試
    -0.06
    POSITIVE LOGITS
    roker
    0.10
    æĪĸ缴æİ¥
    0.08
    ophe
    0.08
    ç¼Ī
    0.07
    æĿ·
    0.07
    estre
    0.07
    ATEST
    0.07
    æijĺç¼ĸ
    0.07
    odef
    0.07
    ¬
    0.07
    Activations Density 0.028%

    No Known Activations