© 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. 46652
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions

    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
    itarian
    -0.08
    iento
    -0.08
    .catch
    -0.07
    å¾ħåľ¨
    -0.07
    åijĨåľ¨
    -0.07
    æijĨåľ¨
    -0.07
     underwater
    -0.07
    ä¹ĭæ¯į
    -0.07
    åľºéĿ¢
    -0.07
    eleri
    -0.07
    POSITIVE LOGITS
    ä½įç½®
    0.12
    ä½įç½®åĴĮ
    0.10
    ä½įç½®çļĦ
    0.10
    çļĦä½įç½®
    0.09
     location
    0.09
    abouts
    0.09
    çŃīå¤Ħ
    0.08
    éĤ£éĩĮ
    0.08
     position
    0.07
    å¾Īè¿ij
    0.07
    Activations Density 0.402%

    No Known Activations