© 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. 56583
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    dden
    -0.08
    æ»´æ»´
    -0.07
    wai
    -0.07
    å»Ī
    -0.07
    æİĸ
    -0.07
    erate
    -0.07
    XXXXXXXX
    -0.07
    XX
    -0.07
    undef
    -0.06
    åIJİå¤ĩ
    -0.06
    POSITIVE LOGITS
     Decompiled
    0.07
    ivot
    0.07
    æĶ¹åıĺçļĦ
    0.07
    ẩm
    0.07
    è¶ĬæĹ©
    0.07
    .duration
    0.06
    ionale
    0.06
    lege
    0.06
    agens
    0.06
    æĿ¥è¶Ĭ
    0.06
    Activations Density 0.010%

    No Known Activations