© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57015
    Prev
    Next
    INDEX
    Explanations

    numerical fractions or divisions

    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
    gnore
    -0.07
    rvine
    -0.07
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.06
    pline
    -0.06
    oft
    -0.06
    ↵        ↵        ↵
    -0.06
    woff
    -0.06
    欢è¿İåħ³æ³¨
    -0.06
    oller
    -0.06
    Ĺı
    -0.06
    POSITIVE LOGITS
    å©ķ
    0.08
    åĽł
    0.08
    è¿ijå¹³
    0.07
    ÃŃž
    0.07
    bian
    0.07
    被
    0.07
     ']
    0.07
    ives
    0.07
    åīįè¿°
    0.07
    ivities
    0.07
    Activations Density 0.016%

    No Known Activations