© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29765
    Prev
    Next
    INDEX
    Explanations

    connecting items with hyphens

    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°Ķé¡¿
    -0.08
    #End
    -0.08
    åĮ»éĻ¢åľ°åĿĢ
    -0.08
    غاÙĦ
    -0.08
    ấn
    -0.08
    รà¸ģิà¸Ī
    -0.08
    angg
    -0.08
    çĸ«æĥħå½±åĵį
    -0.08
    енÑĤи
    -0.08
    ç«ĭå¤ı
    -0.08
    POSITIVE LOGITS
    -to
    0.10
    à¹Ģà¸Ķียว
    0.08
    ually
    0.08
    -in
    0.07
    -
    0.07
    -by
    0.07
    à¸ķรà¸ĩ
    0.07
    âĢIJ
    0.07
    âĢij
    0.07
     “
    0.07
    Activations Density 1.006%

    No Known Activations