© 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. 27263
    Prev
    Next
    INDEX
    Explanations

    less than

    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
    yty
    -0.09
    ç®Ķ
    -0.08
     *–
    -0.08
    cioni
    -0.08
     Warri
    -0.08
    liess
    -0.08
    ç»Ńè´¹
    -0.08
    å°¼æĸ¯
    -0.07
    ongyang
    -0.07
    æĢİä¹ĪåĬŀåij¢
    -0.07
    POSITIVE LOGITS
    imately
    0.07
    çĬ
    0.07
    vre
    0.06
    unca
    0.06
     tand
    0.06
    ÙĩÙĦ
    0.06
    ë¹Ļ
    0.06
    undef
    0.06
     Katherine
    0.06
    éĽĨä½ĵçļĦ
    0.06
    Activations Density 0.025%

    No Known Activations