© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63771
    Prev
    Next
    INDEX
    Explanations

    Euler-type equation

    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
    inste
    -0.09
    罡
    -0.08
    ennt
    -0.08
    ppv
    -0.08
    ç£ķ
    -0.08
    Porno
    -0.07
    newInstance
    -0.07
    lipp
    -0.07
    ç½²
    -0.07
    åIJİæĦŁ
    -0.07
    POSITIVE LOGITS
    æĸĩåºĵ
    0.07
    aza
    0.06
     Barnes
    0.06
     opening
    0.06
    wick
    0.06
     laure
    0.06
    解åĨ³çļĦ
    0.06
    æĺ¯åĪĨ
    0.06
    amps
    0.06
    opening
    0.06
    Activations Density 0.004%

    No Known Activations