© 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. 46632
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving fractions and integrals

    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
    _SUFFIX
    -0.09
    nud
    -0.09
    ebb
    -0.09
    ehren
    -0.08
    åŁºç¤İ
    -0.08
    ople
    -0.08
    åŁºç¡ĢçļĦ
    -0.08
    ovie
    -0.08
     PREFIX
    -0.08
    åŁºç¡Ģ
    -0.08
    POSITIVE LOGITS
    min
    0.06
     even
    0.06
    åįĬè¾¹
    0.06
     Max
    0.06
     doubling
    0.06
     rad
    0.06
    vio
    0.06
    åįĬæķ°
    0.06
    åľ¨ä»»ä½ķ
    0.06
    max
    0.06
    Activations Density 0.007%

    No Known Activations