© 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. 40604
    Prev
    Next
    INDEX
    Explanations

    code identifiers like parentId

    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
    åijĨ
    -0.09
    ehl
    -0.08
    ampf
    -0.07
    ourn
    -0.07
    继æī¿äºº
    -0.07
    AGEN
    -0.07
    Tpl
    -0.07
    alz
    -0.07
    ihak
    -0.07
     Führ
    -0.07
    POSITIVE LOGITS
    och
    0.07
    æŃ£åĢ¼
    0.06
    ä½įåľ¨
    0.06
    æĸĹ
    0.06
    çľĭå¾Ĺ
    0.06
     solic
    0.06
    è¿ĻæĦıåij³çĿĢ
    0.06
    ads
    0.06
    ä¸įå¾ĹäºĨ
    0.06
    adv
    0.06
    Activations Density 0.201%

    No Known Activations