© 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. 32839
    Prev
    Next
    INDEX
    Explanations

    last name

    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
    Ñıн
    -0.08
    lug
    -0.08
    ä½ľåĪĻ
    -0.08
    é¢Ħ
    -0.08
    butt
    -0.08
    ulg
    -0.08
    ledge
    -0.08
    ohl
    -0.07
     rig
    -0.07
     Spann
    -0.07
    POSITIVE LOGITS
    综ä¸Ĭ
    0.07
    äºİæĺ¯å°±
    0.06
    综åIJĪ
    0.06
    åIJĪ计
    0.06
    ared
    0.06
    污æŁĵéĺ²æ²»
    0.06
    åIJĪ并
    0.06
    äºİæĺ¯
    0.06
    äºİæĺ¯ä»ĸ
    0.06
    æĢ»çļĦ
    0.06
    Activations Density 0.086%

    No Known Activations