© 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. 33806
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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
    веÑĤа
    -0.08
    该æĬĢæľ¯
    -0.07
    æĬĢæľ¯çłĶ究
    -0.07
    ibly
    -0.07
    ukai
    -0.07
    _exceptions
    -0.07
    )'),
    -0.07
     UNUSED
    -0.07
    /inc
    -0.07
     Istitu
    -0.07
    POSITIVE LOGITS
    èĩ³å°ij
    0.10
    èµ·çłģ
    0.09
    çļĦè¦ģæ±Ĥ
    0.09
    æľĢèµ·çłģ
    0.09
     atleast
    0.08
     minimum
    0.08
     almeno
    0.08
     setidaknya
    0.08
    minimum
    0.08
    æľĢä½İ
    0.08
    Activations Density 0.008%

    No Known Activations