© 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. 29364
    Prev
    Next
    INDEX
    Explanations

    kids, desire, Inbox, smells, racism, hope, nothing

    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
    æľīä¸Ģå®ļçļĦ
    -0.08
    åıªæĺ¯
    -0.07
    åıªæĺ¯åľ¨
    -0.07
    éĥ½æľīæīĢ
    -0.07
    çĶļèĩ³åľ¨
    -0.07
    æĿ¯æ°´
    -0.07
    åĽ¾çīĩæĪĸ
    -0.06
    æĬķèµĦæĪĸ
    -0.06
    empre
    -0.06
    æĭīæĸ¯
    -0.06
    POSITIVE LOGITS
    ÑģÑĸ
    0.08
     zorgen
    0.07
    (and
    0.07
    äºĮåŃĹ
    0.07
    طر
    0.07
    ä¸İ被
    0.07
    untime
    0.06
    åħįè´¹éĺħ读
    0.06
    äºĭæĪIJ
    0.06
     piled
    0.06
    Activations Density 0.591%

    No Known Activations