© 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. 30314
    Prev
    Next
    INDEX
    Explanations

    intra, post, extra

    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
    åĬłæĭ¿å¤§
    -0.08
    áºŃt
    -0.08
    å¯¹é¡¹çĽ®
    -0.08
    zcz
    -0.07
    iatrics
    -0.07
    俱ä¹IJéĥ¨
    -0.07
    对ç¾İåĽ½
    -0.06
    ä»»åĩŃ
    -0.06
    对产åĵģ
    -0.06
     ìŴ린
    -0.06
    POSITIVE LOGITS
    /*/
    0.09
    人大
    0.08
    åĪĨä¹ĭ
    0.08
    æĹ¥æĿ¥
    0.08
    ä¸įèĥľ
    0.07
    ÑĪнÑĭе
    0.07
    éĩĩ访æŶ
    0.07
    oor
    0.07
    人æĦı
    0.07
    èĢĮ代ä¹ĭ
    0.07
    Activations Density 0.381%

    No Known Activations