© 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. 34127
    Prev
    Next
    INDEX
    Explanations

    numbers preceded by parentheses

    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
    itty
    -0.08
    à¹Ħหม
    -0.07
    íĥĦ
    -0.07
     Pul
    -0.06
    æį¶
    -0.06
    presso
    -0.06
     accept
    -0.06
    æİ¥åıĹ
    -0.06
    ission
    -0.06
    itzer
    -0.06
    POSITIVE LOGITS
     descar
    0.08
    æŨ
    0.08
    gba
    0.08
    ciri
    0.08
    æ¡
    0.08
    ujan
    0.08
    opr
    0.07
    è©¢
    0.07
    صاÙĦ
    0.07
    czo
    0.07
    Activations Density 0.001%

    No Known Activations