© 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. 44953
    Prev
    Next
    INDEX
    Explanations

    quotation start pronoun

    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
    emma
    -0.08
    piring
    -0.08
    ote
    -0.07
    æĦıå¤ĸçļĦ
    -0.07
    +xml
    -0.07
    /client
    -0.07
    initializer
    -0.07
     ngoan
    -0.07
    ä¹ħèĢĮ
    -0.07
    å°ı家
    -0.07
    POSITIVE LOGITS
    éļ»
    0.07
    太太
    0.07
    åĿ¤
    0.06
    ãģĨãģ¡
    0.06
    vj
    0.06
    æĬĬå®ĥ
    0.06
    å°±æĺ¯æĬĬ
    0.06
    eel
    0.06
     screw
    0.06
    rid
    0.06
    Activations Density 0.345%

    No Known Activations