© 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. 63438
    Prev
    Next
    INDEX
    Explanations

    slit, dot, light, slot, feeder, rails

    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
    adona
    -0.09
    åĴĸ
    -0.08
    ardown
    -0.08
    gzip
    -0.08
    gris
    -0.08
    ائØŃ
    -0.08
    ebo
    -0.08
    verted
    -0.07
    EMENT
    -0.07
    aning
    -0.07
    POSITIVE LOGITS
    éĹ´è·Ŀ
    0.08
    缸è·Ŀ
    0.07
     spaced
    0.07
     arras
    0.07
    ä¹ĭéĹ´çļĦè·Ŀ离
    0.07
    å®ŀéªĮä¸Ń
    0.06
    åIJİ人
    0.06
    ain
    0.06
     aure
    0.06
    éĹ´éļĶ
    0.06
    Activations Density 0.003%

    No Known Activations