© 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. 58352
    Prev
    Next
    INDEX
    Explanations

    statistical analysis and classification

    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
    åĥıä½ł
    -0.07
     certas
    -0.07
    æĦ¿ä½ł
    -0.07
     ÙħعÙĬÙĨØ©
    -0.07
    éĤ£éĩĮçļĦ
    -0.07
    æŁIJäºĽ
    -0.07
     certos
    -0.07
    verhalten
    -0.07
    æ¯Ķå¦Ĥ说
    -0.07
    æŁIJç§į
    -0.07
    POSITIVE LOGITS
     admittedly
    0.09
    (Table
    0.09
     Fig
    0.09
    Fig
    0.08
    欺
    0.07
     purposely
    0.07
     unavoid
    0.07
    (fig
    0.07
    AUTH
    0.07
    Ngh
    0.07
    Activations Density 0.326%

    No Known Activations