© 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. 55804
    Prev
    Next
    INDEX
    Explanations

    collapse

    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
    áĥķáĥľ
    -0.08
    ãĢħãģ®
    -0.08
    ativamente
    -0.08
    aner
    -0.08
    é«ĺ人
    -0.07
    kannya
    -0.07
    ỾI
    -0.07
    illard
    -0.07
    anou
    -0.07
    ubat
    -0.07
    POSITIVE LOGITS
    æ»ĵ
    0.08
     onto
    0.07
    esa
    0.07
    æĪIJä¸Ģ个
    0.07
    ิà¸Ļà¸Ĺรà¹Į
    0.07
    /exp
    0.07
    æĪIJä¸Ģ
    0.07
    gica
    0.07
    åĪ°ä¸Ģèµ·
    0.07
    å¦Ĥå±±
    0.07
    Activations Density 0.015%

    No Known Activations