© 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. 1544
    Prev
    Next
    INDEX
    Explanations

    zyd or woo or Sands

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.21
    ãĤĪãģĨãģª
    -0.19
    ä¸Ģ个
    -0.14
    ãĥ£
    -0.14
    ом
    -0.13
    ãĤĪãģĨãģ«
    -0.13
    äºĨ
    -0.13
    人
    -0.12
    gether
    -0.12
    ãĥ£ãĥ³
    -0.11
    POSITIVE LOGITS
    ing
    0.22
    i
    0.18
    à§ĩ
    0.17
    àµį
    0.17
    и
    0.17
    iés
    0.17
    ÙĬ
    0.17
    ãĥ¼
    0.16
    à¯į
    0.16
    a
    0.15
    Activations Density 3.823%

    No Known Activations