© 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. 30832
    Prev
    Next
    INDEX
    Explanations

    orthogonal, cone programs, blood Hollow, parabolic partial

    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
    éĴ£
    -0.09
    croft
    -0.07
    京åŁİ
    -0.07
    wares
    -0.07
    æ¦Ķ
    -0.07
    mium
    -0.07
    oooooooo
    -0.07
    방침
    -0.07
    etek
    -0.06
    -location
    -0.06
    POSITIVE LOGITS
     Pas
    0.07
    Pas
    0.07
    ç¦ģ
    0.07
    angu
    0.06
    åѦçĶŁå®¶éķ¿
    0.06
     tract
    0.06
     Nexus
    0.06
    mail
    0.06
    /twitter
    0.06
    /non
    0.06
    Activations Density 0.001%

    No Known Activations