© 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. 10797
    Prev
    Next
    INDEX
    Explanations

    numbers and letters

    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
    akai
    -0.07
    uger
    -0.07
    ignano
    -0.07
     ròng
    -0.07
    ;amp
    -0.06
    ithe
    -0.06
    onen
    -0.06
    verband
    -0.06
    atcher
    -0.06
    ToFile
    -0.06
    POSITIVE LOGITS
    scher
    0.07
    æł·æł·
    0.07
    èĶĹ
    0.07
    á»ģ
    0.07
    appe
    0.07
    èĸ«
    0.07
     appeal
    0.06
    à´¦àµį
    0.06
    ãģĭãĤĵ
    0.06
    ücks
    0.06
    Activations Density 0.004%

    No Known Activations