© 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. 13708
    Prev
    Next
    INDEX
    Explanations

    numerical dates and quantities

    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
    第ä¸Ģéĥ¨
    -0.07
    ä¸į严
    -0.06
     sÃŃ
    -0.06
    éĥ¨
    -0.06
    bound
    -0.06
    æī©
    -0.06
    abyrinth
    -0.06
     mü
    -0.06
    æĶ¾çľ¼
    -0.06
    æ³°
    -0.06
    POSITIVE LOGITS
     descending
    0.08
    åī¯ç»Ħéķ¿
    0.08
    anship
    0.08
     downs
    0.08
    addir
    0.08
    Äįia
    0.07
    æĥ¹äºº
    0.07
    менÑĮ
    0.07
    tam
    0.07
    æĥ³å¾Ĺ
    0.07
    Activations Density 0.391%

    No Known Activations