© 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. 11910
    Prev
    Next
    INDEX
    Explanations

    ratio of

    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
    æ¯ıä¸Ģ个人
    -0.08
     controversy
    -0.08
    [text
    -0.07
    azzo
    -0.07
    ÑĢад
    -0.07
    ãģĿãģ®ä»ĸ
    -0.07
    fait
    -0.07
    agement
    -0.07
    моÑģ
    -0.07
    inalg
    -0.07
    POSITIVE LOGITS
     two
    0.11
    çļĦ两个
    0.10
    两个
    0.10
     sexes
    0.09
     respective
    0.09
     duas
    0.08
    æĸ°æŧ
    0.08
    两份
    0.08
     densities
    0.08
    åĪĨåĪ«ä¸º
    0.08
    Activations Density 0.077%

    No Known Activations