© 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. 55473
    Prev
    Next
    INDEX
    Explanations

    numbers with punctuation and symbols

    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
     amongst
    -0.07
    oron
    -0.07
    ä¸įå¼ĥ
    -0.07
    erei
    -0.07
    çĭ®
    -0.07
    åĦ¿çļĦ
    -0.07
    OLOR
    -0.07
    ereien
    -0.06
    æľºåħ³
    -0.06
    FORMATION
    -0.06
    POSITIVE LOGITS
    oad
    0.07
    aiss
    0.07
    iams
    0.07
    æģĻ
    0.07
    obl
    0.06
    èĴĤæĸ¯
    0.06
    æ¯Ĵ
    0.06
    _DLL
    0.06
    æ½®
    0.06
     inv
    0.06
    Activations Density 0.046%

    No Known Activations