© 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. 12300
    Prev
    Next
    INDEX
    Explanations

    chemical formulas with parentheses

    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
    ertz
    -0.06
    =>
    -0.06
    袴
    -0.06
    oplan
    -0.06
    èĨĽ
    -0.06
     pequ
    -0.06
    æ´Ľå¤«
    -0.06
    'd
    -0.06
    åĬ²
    -0.06
    ikä
    -0.05
    POSITIVE LOGITS
    è¿ŀæİ¥æľī
    0.08
    acias
    0.08
    å¹³éĺ³
    0.08
    ÙIJÙĬÙİ
    0.08
    ÑĢеа
    0.08
    æĪĸå°ij
    0.07
    lang
    0.07
    禦
    0.07
    ä¸Ń天
    0.07
    _impl
    0.07
    Activations Density 0.123%

    No Known Activations