© 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. 28022
    Prev
    Next
    INDEX
    Explanations

    output file names or descriptions

    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
    æĻ®éĢļçļĦ
    -0.07
    åŃ½
    -0.06
    essim
    -0.06
    hold
    -0.06
    没æľīåĬŀæ³ķ
    -0.06
    æĿ¥æºIJäºİç½ij绾
    -0.06
    æīĵåĪ°
    -0.06
    bum
    -0.06
    æľīçļĦæŶåĢĻ
    -0.06
    romise
    -0.06
    POSITIVE LOGITS
    antro
    0.08
    ekh
    0.08
    ekat
    0.08
    lator
    0.08
    eke
    0.08
    keer
    0.07
    ç´§è·Ł
    0.07
    çļĦ第ä¸Ģ
    0.07
    herits
    0.07
     reordered
    0.07
    Activations Density 0.009%

    No Known Activations