© 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. 15777
    Prev
    Next
    INDEX
    Explanations

    recall that

    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
    heber
    -0.08
    enticate
    -0.08
    رج
    -0.07
    nable
    -0.07
    æĪij以åIJİ
    -0.07
    åĥıä½ł
    -0.07
    eenth
    -0.07
    ihad
    -0.07
    åĪļåĪļ好
    -0.07
    artment
    -0.07
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.08
    ////////////////////////////////////////////////////////
    0.08
    ç»ıåħ¸çļĦ
    0.08
    ãĤĪãģĨãģ«
    0.07
     rằng
    0.07
    definition
    0.07
     bahwa
    0.07
    oura
    0.07
     definitions
    0.07
    ä¸įåĨ³
    0.07
    Activations Density 0.008%

    No Known Activations