© 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. 60765
    Prev
    Next
    INDEX
    Explanations

    math or code exponents

    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
    /class
    -0.07
    aus
    -0.06
    åħ·æľīè¾ĥé«ĺçļĦ
    -0.06
    æķ¢
    -0.06
    rop
    -0.05
    éĥ
    -0.05
    anze
    -0.05
     nanti
    -0.05
    ang
    -0.05
    auer
    -0.05
    POSITIVE LOGITS
    issen
    0.08
    åŁºæĸ¯åĿ¦
    0.08
    ousy
    0.08
    ächt
    0.07
    essos
    0.07
    κÏģα
    0.07
    onsin
    0.07
    ÃŃss
    0.07
    osat
    0.07
    士æŀĹ
    0.07
    Activations Density 0.077%

    No Known Activations