© 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. 32409
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    ä¾
    -0.08
     Haram
    -0.07
    ecos
    -0.07
    YO
    -0.07
    еÑĨ
    -0.06
    eping
    -0.06
    Ïĥια
    -0.06
     جر
    -0.06
    ód
    -0.06
     Dtype
    -0.06
    POSITIVE LOGITS
    âĸ·
    0.08
    ureka
    0.08
    queira
    0.07
    åĽ½åľŁ
    0.07
     Ãģngeles
    0.07
    askets
    0.07
    以任ä½ķ
    0.07
    gli
    0.07
    bred
    0.06
    Alias
    0.06
    Activations Density 0.027%

    No Known Activations