© 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. 9387
    Prev
    Next
    INDEX
    Explanations

    for each

    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
    mana
    -0.07
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.07
    aidu
    -0.07
    ä¿¡æģ¯çĶ±
    -0.07
    ä¹ĭå·ħ
    -0.06
    AuthToken
    -0.06
    çIJ¥
    -0.06
    家æĺ¯
    -0.06
    neur
    -0.06
     Lees
    -0.06
    POSITIVE LOGITS
    æ¯ıä¸Ģç§į
    0.08
    æ¯ıä¸Ģ份
    0.08
    æ¯ıä¸Ģ个
    0.08
     everything
    0.08
     everytime
    0.08
     each
    0.07
    æ¯ıç§į
    0.07
    ëijĺ
    0.07
     wherever
    0.07
    bose
    0.07
    Activations Density 0.134%

    No Known Activations