© 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. 21778
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with powers

    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
    urig
    -0.07
    çĩķ
    -0.06
    ëĮĢë¡ľ
    -0.06
     Cave
    -0.06
     events
    -0.06
    æĺ¥å¤ıç§ĭåĨ¬
    -0.06
    è¿ŀéĶģ
    -0.06
    æ²¹
    -0.06
    olat
    -0.06
     eman
    -0.06
    POSITIVE LOGITS
     variable
    0.08
    arsers
    0.07
    项
    0.07
     nett
    0.07
    asti
    0.07
    åĪĴ
    0.07
     esclar
    0.07
    avais
    0.07
     factor
    0.07
    pine
    0.07
    Activations Density 0.004%

    No Known Activations