© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14627
    Prev
    Next
    INDEX
    Explanations

    scale value `.png`

    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
    è¯ģæį®è¯ģæĺİ
    -0.08
    åľ¨åIJij
    -0.07
    èĢģå¸Īåľ¨
    -0.07
     infatti
    -0.07
    ÙĮ
    -0.07
    å¾Ī大ç¨ĭ度ä¸Ĭ
    -0.07
    çļĦä¸ĢåĪĩéĥ½
    -0.07
     Zel
    -0.07
     Weiner
    -0.06
     Scha
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.07
     vůbec
    0.07
    (PyObject
    0.06
     downright
    0.06
    ä¹Łæĺ¯åįģåĪĨ
    0.06
     ê²½ìļ°ìĹIJëĬĶ
    0.06
    ä¹ŁåįģåĪĨ
    0.06
     à¹Ģลย
    0.06
    ewnÄĻ
    0.06
    лко
    0.06
    Activations Density 0.274%

    No Known Activations