© 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. 22278
    Prev
    Next
    INDEX
    Explanations

    results, spectra, charge, dose, decay

    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
     pula
    -0.07
     kelamin
    -0.06
    ↵
    -0.06
    amol
    -0.06
    ench
    -0.06
    arks
    -0.05
    æĸ°çļĦ
    -0.05
    rement
    -0.05
    flies
    -0.05
    Âł
    -0.05
    POSITIVE LOGITS
    æĪij社
    0.09
    urs
    0.08
    TypeError
    0.08
    å·¥ç¨ĭéĻ¢
    0.07
    -disable
    0.07
    ÙĦÙģ
    0.07
    clare
    0.07
     Unblock
    0.07
    elic
    0.07
    uring
    0.07
    Activations Density 0.200%

    No Known Activations