© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46627
    Prev
    Next
    INDEX
    Explanations

    HTML list items and table data

    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
    икÑĢо
    -0.08
    æĢĢ
    -0.08
    ç¼Ŀ
    -0.07
    å¾·æĻº
    -0.07
    заÑħ
    -0.07
    izzo
    -0.07
     gal
    -0.07
     opu
    -0.07
    achel
    -0.07
    æľĢ令人
    -0.07
    POSITIVE LOGITS
     Tisch
    0.07
    idora
    0.07
     ((__
    0.06
    æ°¸å®ī
    0.06
    autoload
    0.06
     Jorn
    0.06
    ημα
    0.06
    cano
    0.06
    çĮ©
    0.06
    zers
    0.06
    Activations Density 0.008%

    No Known Activations