© 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. 27280
    Prev
    Next
    INDEX
    Explanations

    defining sections or parts

    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
    ราà¸Ĭà¸ģาร
    -0.08
    quals
    -0.07
    ä¸į离
    -0.07
    空æ°Ķä¸ŃçļĦ
    -0.07
    åİ¿å§Ķåī¯ä¹¦è®°
    -0.07
    åħ¶ä»ĸæĸ¹å¼ı
    -0.06
    æĽ´å¤§çļĦ
    -0.06
    ree
    -0.06
    inox
    -0.06
    空æ°Ķä¸Ń
    -0.06
    POSITIVE LOGITS
     section
    0.11
     Section
    0.10
    Section
    0.10
    -section
    0.09
    section
    0.09
    .section
    0.09
    _section
    0.09
     sezione
    0.09
    _SECTION
    0.09
     subsection
    0.09
    Activations Density 0.626%

    No Known Activations