© 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. 2284
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables and operators

    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
    èĤ¡çļĦ
    -0.07
    \\\
    -0.07
    rix
    -0.07
     xuôi
    -0.07
    émat
    -0.06
    otron
    -0.06
    иÑģло
    -0.06
    åĽ°éļ¾åĴĮéĹ®é¢ĺ
    -0.06
    Sharing
    -0.06
    ilik
    -0.06
    POSITIVE LOGITS
     gider
    0.08
    è°¤
    0.08
    ä¸įçIJĨ
    0.08
     Damon
    0.07
    ãĥ©ãĥ¼
    0.07
    laf
    0.07
    稽
    0.07
    _DER
    0.07
    itier
    0.07
     imprison
    0.07
    Activations Density 0.037%

    No Known Activations