© 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. 4095
    Prev
    Next
    INDEX
    Explanations

    error messages and legal disclaimers

    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
    ìį¨
    -0.12
    ork
    -0.11
    ord
    -0.10
    ãĢħãģ®
    -0.10
    wards
    -0.10
    à¹Ĩ
    -0.10
    ument
    -0.09
    rid
    -0.09
    -fashioned
    -0.09
     à¹Ĩ
    -0.09
    POSITIVE LOGITS
    mente
    0.11
    alize
    0.10
    aires
    0.10
    alization
    0.09
    Ñİ
    0.09
    aire
    0.09
    al
    0.09
    cini
    0.08
    ků
    0.08
    hips
    0.08
    Activations Density 19.485%

    No Known Activations