© 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. 25512
    Prev
    Next
    INDEX
    Explanations

    academic level or course context

    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
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.09
    RIES
    -0.09
    mpr
    -0.08
    heber
    -0.08
    angs
    -0.08
    ubern
    -0.08
    éªĩ
    -0.08
    yman
    -0.08
    renom
    -0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.08
    POSITIVE LOGITS
    è¯¾æľ¬
    0.08
     taught
    0.07
    éĩįçĤ¹
    0.07
    人æķĻçīĪ
    0.07
     textbook
    0.07
    æİĮæı¡
    0.07
    lesson
    0.07
    ãĢĬ
    0.06
    çŁ¥è¯ĨçĤ¹
    0.06
     Activ
    0.06
    Activations Density 0.015%

    No Known Activations