© 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. 12629
    Prev
    Next
    INDEX
    Explanations

    simplify followed by mathematical expressions

    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
    voz
    -0.09
    icken
    -0.09
    uguay
    -0.08
    åĽ°éļ¾åĴĮéĹ®é¢ĺ
    -0.08
    Äħtek
    -0.08
    adeiras
    -0.07
    被å°ģ
    -0.07
    hões
    -0.07
    æ³ķå¾ĭä¿ĿæĬ¤
    -0.07
    ippet
    -0.07
    POSITIVE LOGITS
    able
    0.08
    ible
    0.08
    åIJİçļĦ
    0.07
    /max
    0.06
    ç®
    0.06
    uart
    0.06
    ç¨ĭ度
    0.06
    æĹ¥çĶ¨
    0.06
    ant
    0.06
    iche
    0.06
    Activations Density 0.014%

    No Known Activations