© 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. 47867
    Prev
    Next
    INDEX
    Explanations

    management, tech, Math

    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
    orea
    -0.08
    à¹ģ
    -0.08
    ãĥ¼ãĥĪãĥ«
    -0.07
    erala
    -0.07
    arella
    -0.07
    ادث
    -0.07
    ç²¹
    -0.07
    AGMA
    -0.07
    adians
    -0.07
    à¦ļিত
    -0.07
    POSITIVE LOGITS
    常çĶ¨çļĦ
    0.07
    zi
    0.06
    æ´ĭ
    0.06
    ya
    0.06
    lay
    0.06
     Huff
    0.06
    æķ°çIJĨ
    0.06
    æ¨ĭ
    0.06
    大æ´ĭ
    0.06
    ooke
    0.06
    Activations Density 0.002%

    No Known Activations