© 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. 60461
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and infinity

    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
    aty
    -0.08
    .Unmarshal
    -0.08
    quil
    -0.08
    转贴
    -0.08
     Smarty
    -0.08
    lej
    -0.07
    óg
    -0.07
    azel
    -0.07
    Tween
    -0.07
    年第
    -0.07
    POSITIVE LOGITS
    èįĴ
    0.08
     infinite
    0.08
    åºĶå½ĵä¾Ŀçħ§
    0.07
     violent
    0.07
     stabilization
    0.07
     improper
    0.07
    å´©
    0.07
     stabilized
    0.07
     беÑģ
    0.07
    Attempt
    0.06
    Activations Density 0.012%

    No Known Activations