© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50023
    Prev
    Next
    INDEX
    Explanations

    SVG path data

    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
    coc
    -0.08
    ÙĪسÙĬ
    -0.08
    ä¸ĢåĪĨéĴ±
    -0.08
    éns
    -0.08
    ank
    -0.08
    èĢģåĮº
    -0.08
    èĬĤèĬĤ
    -0.07
    é½¢
    -0.07
    änk
    -0.07
    à¸ĩ
    -0.07
    POSITIVE LOGITS
    åĽ½éŨ
    0.07
    鸥
    0.07
    æĪijæĦ¿
    0.06
    ç§ijåѦåıijå±ķè§Ĥ
    0.06
    é»Ħæ¢ħ
    0.06
    ust
    0.06
    ек
    0.06
    usche
    0.06
    icing
    0.06
    æī¿
    0.06
    Activations Density 0.005%

    No Known Activations