© 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. 63407
    Prev
    Next
    INDEX
    Explanations

    I'm or this is

    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
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.08
    æĪĸ以
    -0.07
    igits
    -0.07
    ä¸į以
    -0.07
    avig
    -0.07
    اÙħÙĨ
    -0.07
    elsing
    -0.07
    sect
    -0.07
    ece
    -0.07
    ä¸įèĥľ
    -0.07
    POSITIVE LOGITS
    æĺ¯å¦Ĥä½ķ
    0.08
    æĦıä¹īçļĦ
    0.08
     nuanced
    0.07
    羣æŃ£
    0.07
    fit
    0.07
    å¦Ĥä½ķ让
    0.07
     meaningful
    0.06
    èĢĮæĺ¯è¦ģ
    0.06
    how
    0.06
    ucid
    0.06
    Activations Density 0.026%

    No Known Activations