© 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. 11805
    Prev
    Next
    INDEX
    Explanations

    increases, restores, enhances

    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
    åħ¬åħ±æľįåĬ¡
    -0.07
    è¿Ľä¸ĢæŃ¥åĬłå¼º
    -0.07
    pleted
    -0.07
    æľįåĬ¡ä¿Ŀéļľ
    -0.07
    elaar
    -0.07
    iecz
    -0.07
    ãģĹãģ¦ãĤĤãĤīãģĨ
    -0.07
     myself
    -0.07
    ç»Īäºİåľ¨
    -0.07
     segÃŃtség
    -0.07
    POSITIVE LOGITS
    umenta
    0.08
     indem
    0.08
    ort
    0.08
    verts
    0.07
    åĩŃåĢŁåħ¶
    0.07
    sts
    0.07
     havoc
    0.07
    åĵªäºĽæĸ¹éĿ¢
    0.07
     tellement
    0.07
    æıIJä¾ĽäºĨä¸Ģç§į
    0.07
    Activations Density 0.269%

    No Known Activations