© 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. 56540
    Prev
    Next
    INDEX
    Explanations

    mathematical and code symbols

    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
    shoot
    -0.08
    çļĦéĢļçŁ¥
    -0.07
    roma
    -0.07
    à¸Ħา
    -0.07
    otto
    -0.06
     RESERVED
    -0.06
    ç»Ĵ
    -0.06
    å°Ĩä¸Ģ个
    -0.06
    anj
    -0.06
    èĩº
    -0.06
    POSITIVE LOGITS
    oment
    0.10
    -Allow
    0.07
    alaria
    0.07
    owie
    0.07
     suscep
    0.07
    ç¡®
    0.07
    íĹĪ
    0.07
    ÏĨη
    0.07
    ufig
    0.07
    å±ķ
    0.07
    Activations Density 0.004%

    No Known Activations