© 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. 25471
    Prev
    Next
    INDEX
    Explanations

    crossOrigin perm 1

    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
    utow
    -0.07
    çļĦæ¸ħ
    -0.07
    æĸ·
    -0.07
    åį°
    -0.07
    é¾Ī
    -0.07
    è¿Ľç¤¾åĮº
    -0.07
     laufenden
    -0.07
    羣å®ŀæĢ§è´Łè´£
    -0.06
     Gros
    -0.06
    жеÑĤ
    -0.06
    POSITIVE LOGITS
    ÑĢед
    0.07
    มà¸ĩà¸Ħล
    0.07
    æ´Ľåħĭ
    0.07
    ifter
    0.07
    Locator
    0.07
     Maz
    0.06
    çģŃ
    0.06
    æ¶ħ
    0.06
    ÑĤи
    0.06
    èİİæĭī
    0.06
    Activations Density 0.767%

    No Known Activations