© 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. 14156
    Prev
    Next
    INDEX
    Explanations

    pronunciation or technical terms

    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
    iecz
    -0.09
    ç½ijç«Ļåľ°åĽ¾
    -0.08
    iral
    -0.08
    温æŁĶ
    -0.08
    heid
    -0.07
    hift
    -0.07
    éĿ¢æİĪ
    -0.07
    ERCHANT
    -0.07
    films
    -0.07
    åħ¥ç¾¤
    -0.07
    POSITIVE LOGITS
    chn
    0.07
    æѤå¤Ħ
    0.07
    ä¸ĭè§Ĵ
    0.06
    æĮĩ
    0.06
    æĸĩä¸ŃçļĦ
    0.06
    åĴĮæĦıä¹ī
    0.06
    让人è§īå¾Ĺ
    0.06
    ä¸ĢèĪ¬æĿ¥è¯´
    0.06
    è¿ĻéĩĮæĺ¯
    0.06
    åģļèµ·
    0.06
    Activations Density 0.108%

    No Known Activations