© 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. 48861
    Prev
    Next
    INDEX
    Explanations

    discount

    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
    upert
    -0.09
    schaft
    -0.08
     اÙĦÙħتØŃدة
    -0.08
    ÙĪÙĬات
    -0.08
    reland
    -0.08
    udeau
    -0.08
    kamer
    -0.08
    à¤Ĺत
    -0.08
    ัà¸ģษ
    -0.08
    ä¸ĭéĿ¢å°ıç¼ĸ
    -0.08
    POSITIVE LOGITS
    ingly
    0.11
    ombre
    0.09
    ers
    0.08
    ed
    0.08
    /free
    0.07
    ably
    0.07
    atamente
    0.07
    able
    0.07
    /pre
    0.07
    ing
    0.07
    Activations Density 0.009%

    No Known Activations