© 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. 27326
    Prev
    Next
    INDEX
    Explanations

    currently in, on, or under

    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
    æīĵå¾Ĺ
    -0.08
    åĩŃèIJ¥ä¸ļæī§çħ§
    -0.07
    [Unit
    -0.07
    çĿ¡å¾Ĺ
    -0.07
    æīĵçļĦ
    -0.07
     angeg
    -0.07
     spre
    -0.07
    [^
    -0.07
    éĻIJ
    -0.06
    æīĵäºĨ个
    -0.06
    POSITIVE LOGITS
    çķĻåľ¨
    0.12
    åŃĺåľ¨äºİ
    0.12
    åĩºçİ°åľ¨
    0.12
     presence
    0.11
    appendTo
    0.10
    à¸Ńยูà¹Īà¹ĥà¸Ļ
    0.10
    ÙĪاجد
    0.09
    åĩºçı¾åľ¨
    0.09
     onto
    0.09
    åĬŁäºİ
    0.08
    Activations Density 0.469%

    No Known Activations