© 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. 40305
    Prev
    Next
    INDEX
    Explanations

    notifications or IDs

    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
    enders
    -0.07
    frei
    -0.07
    è¿Ŀ
    -0.07
    &(
    -0.07
    perc
    -0.06
    หà¸Ļ
    -0.06
    çĭ¬çī¹çļĦ
    -0.06
    eke
    -0.06
    诡
    -0.06
    ç³ĸå°¿
    -0.06
    POSITIVE LOGITS
    à¹Ģหลืà¸Ń
    0.07
    æ·ĭæ¼ĵ
    0.07
    allar
    0.07
    ieux
    0.07
    å¨ħ
    0.07
    bb
    0.06
    æĸ°æĺŁ
    0.06
    åĵºèĤ²
    0.06
     Pad
    0.06
    鳩
    0.06
    Activations Density 0.008%

    No Known Activations