© 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. 9485
    Prev
    Next
    INDEX
    Explanations

    behooves, nigh, unto, whence

    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
    缸è¾ħ缸æĪIJ
    -0.09
    QÄIJ
    -0.08
    subpackage
    -0.08
    oleon
    -0.08
    ä¸įåı¯æĢĿè®®
    -0.07
    iá»ģm
    -0.07
    ovn
    -0.07
    icati
    -0.07
     Verbra
    -0.07
    êµīìŀ¥
    -0.07
    POSITIVE LOGITS
    è§ģå¾Ĺ
    0.09
     tale
    0.09
    æŶæĹ¥
    0.09
     whence
    0.09
    è¿ĻèĪ¬
    0.09
    ä½ķå¤Ħ
    0.09
     unto
    0.09
    ä½ķç§į
    0.08
     chiefly
    0.08
    åĵī
    0.08
    Activations Density 2.023%

    No Known Activations