© 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. 31974
    Prev
    Next
    INDEX
    Explanations

    numbers 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
    umul
    -0.07
    ä¸į失
    -0.07
    æ¾İæ¹ĥæĸ°éĹ»
    -0.07
    æī©å±ķèµĦæĸĻ
    -0.07
    èģĶ欢
    -0.07
    нÑĨи
    -0.07
    ä¸įçĪ½
    -0.07
    ifecycle
    -0.06
    ":-
    -0.06
    wick
    -0.06
    POSITIVE LOGITS
    ç£ĭ
    0.07
    é»Ķ
    0.07
    ÑģÑĤеÑĢ
    0.07
    ekat
    0.06
    说åĪ°
    0.06
    ä¸īéŨ
    0.06
    STYPE
    0.06
    uces
    0.06
    æģ³
    0.06
    åĨĻåĪ°
    0.06
    Activations Density 0.011%

    No Known Activations