© 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. 43919
    Prev
    Next
    INDEX
    Explanations

    api, url, cgi, shell

    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
    è°´
    -0.06
    orno
    -0.06
    kend
    -0.06
    Others
    -0.06
     Pelle
    -0.06
    ruk
    -0.06
    并åħ¥
    -0.06
    RO
    -0.06
    åıįåĢĴæĺ¯
    -0.06
     незавиÑģимо
    -0.06
    POSITIVE LOGITS
    almas
    0.08
    ufr
    0.07
    morgan
    0.07
     Jup
    0.07
    Ùħص
    0.07
    æĺķ
    0.07
    -uri
    0.07
    usercontent
    0.07
     trÆ°Æ¡ng
    0.07
    åįģ足
    0.07
    Activations Density 0.125%

    No Known Activations