© 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. 57509
    Prev
    Next
    INDEX
    Explanations

    different distinct variations

    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
    åIJįåī¯åħ¶å®ŀçļĦ
    -0.08
    èĸ°
    -0.08
    ignano
    -0.07
    inkan
    -0.07
    æŀģ好
    -0.07
    ÙĨدر
    -0.07
    atera
    -0.07
     exclus
    -0.07
     technische
    -0.07
    æĢĿæĥ³ä¸Ĭ
    -0.07
    POSITIVE LOGITS
     different
    0.16
    ä¸įåIJĮçļĦ
    0.14
    ä¸įåIJĮ
    0.13
    different
    0.12
     diferente
    0.11
     diferentes
    0.11
    çī¹å®ļ
    0.11
     Different
    0.10
    çļĦä¸įåIJĮ
    0.10
     unterschied
    0.10
    Activations Density 0.353%

    No Known Activations