© 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. 46221
    Prev
    Next
    INDEX
    Explanations

    date, function, mathematical expressions, code snippets

    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
    ipl
    -0.08
    #w
    -0.08
    blr
    -0.07
    ä¸Ģ缮
    -0.07
    egram
    -0.07
    æĺ¯èĢģ
    -0.07
    пеÑĨ
    -0.07
    leti
    -0.07
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    -0.07
    .hasOwnProperty
    -0.07
    POSITIVE LOGITS
    æĶ¶åĪ°
    0.07
    ilities
    0.07
    éħ
    0.06
    声
    0.06
    åĤ¬æĶ¶
    0.06
    责任æĦŁ
    0.06
    ylie
    0.06
    appa
    0.06
     abs
    0.06
    ister
    0.06
    Activations Density 0.088%

    No Known Activations