© 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. 45904
    Prev
    Next
    INDEX
    Explanations

    superlatives

    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
    æĢ»æ¯Ķ
    -0.08
     somewhere
    -0.07
    caya
    -0.07
    Meta
    -0.07
    sworth
    -0.07
    è¹´
    -0.07
    åħĦéķ¿
    -0.07
    yne
    -0.07
    æŁIJç§į
    -0.07
    eningen
    -0.06
    POSITIVE LOGITS
    åĴĮæľĢ
    0.14
    ä¹Łæĺ¯æľĢ
    0.09
     ÑģамÑĭе
    0.09
    æľĢæ·±çļĦ
    0.09
     deepest
    0.09
     СамÑĭе
    0.09
    æľĢæ·±
    0.09
    çĶ¨æľĢ
    0.09
    hest
    0.09
    most
    0.09
    Activations Density 0.296%

    No Known Activations