© 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. 65082
    Prev
    Next
    INDEX
    Explanations

    referring to "it" or quotes

    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
    ugno
    -0.08
    žÃŃv
    -0.08
    åĵī
    -0.08
    ;amp
    -0.07
    æĵİ
    -0.07
    æ¯Ķæĸ¹
    -0.07
    迪æĸ¯
    -0.07
    *”.
    -0.07
    aglia
    -0.07
    Öģ
    -0.07
    POSITIVE LOGITS
     referring
    0.09
    æĮĩçļĦæĺ¯
    0.08
     refers
    0.08
    æĮĩçĿĢ
    0.07
    æĺ¯æĮĩåľ¨
    0.07
    æĮĩ
    0.07
    ä¸Ģè¯į
    0.07
     instead
    0.07
     followed
    0.07
    ities
    0.06
    Activations Density 0.031%

    No Known Activations