© 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. 28700
    Prev
    Next
    INDEX
    Explanations

    linear and quadratic combinations

    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
     Wise
    -0.07
    ί
    -0.07
    haft
    -0.07
    紧紧çļĦ
    -0.07
    inate
    -0.07
     Prós
    -0.06
    UDA
    -0.06
    ä»Ĭ
    -0.06
    èĴ¸èĴ¸
    -0.06
    çݺ
    -0.06
    POSITIVE LOGITS
    /non
    0.09
    åĴĮéĿŀ
    0.09
    ä¸İéĿŀ
    0.09
    -linear
    0.08
     admitting
    0.08
    linear
    0.08
     admit
    0.08
    enheim
    0.08
    线æĢ§
    0.08
     linear
    0.07
    Activations Density 0.013%

    No Known Activations