© 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. 27184
    Prev
    Next
    INDEX
    Explanations

    minor matrix

    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
     anthrop
    -0.07
    arts
    -0.07
    綱
    -0.06
    ÙĨداÙĨ
    -0.06
     slug
    -0.06
    unny
    -0.06
    icht
    -0.06
    attrs
    -0.06
     skim
    -0.06
     fl
    -0.06
    POSITIVE LOGITS
    arry
    0.08
    声åĻ¨
    0.07
    缸åºĶ
    0.07
     Bite
    0.07
    对åºĶçļĦ
    0.07
    etest
    0.07
    对åºĶ
    0.07
    æĹłæĢ¨
    0.07
    (EXPR
    0.07
     corresponding
    0.07
    Activations Density 0.001%

    No Known Activations