© 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. 51412
    Prev
    Next
    INDEX
    Explanations

    medical, technical, or system terms

    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
    ä¸įè¡°
    -0.08
    _AXIS
    -0.08
    æįĮ
    -0.07
    纳æĸ¯
    -0.07
    æŃ¤èµ·
    -0.07
    epas
    -0.07
    /address
    -0.07
    æĵįä½ľæĢ§
    -0.07
    åĴĮèĥ½åĬĽ
    -0.07
    issen
    -0.07
    POSITIVE LOGITS
    åĴĮ大
    0.07
    à¹ģà¸¥à¸°à¸ľà¸¹à¹ī
    0.06
    åĴ¯
    0.06
    etz
    0.06
    éľĦ
    0.06
    .calculate
    0.06
    erman
    0.06
    æľ«
    0.06
    åĴĮåĵģçīĮ
    0.06
    ustum
    0.06
    Activations Density 0.026%

    No Known Activations