© 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. 49827
    Prev
    Next
    INDEX
    Explanations

    titles and authors

    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
    æ¢ħæŀĹ
    -0.07
     natal
    -0.07
    åĽŀäºĭ
    -0.07
    âtre
    -0.07
     caught
    -0.07
    utzt
    -0.07
    flies
    -0.06
    ä¸įæį¢
    -0.06
    ekar
    -0.06
    ظÙħ
    -0.06
    POSITIVE LOGITS
    ç§
    0.08
    uelle
    0.08
    éĢļ讯å½ķ
    0.07
    osting
    0.07
    Ĥ¬
    0.07
    çĽ¸ä¼¼æĸĩçĮ®
    0.07
     bero
    0.07
    ãĥŀãĤ¤
    0.07
    ¿IJ
    0.06
    deles
    0.06
    Activations Density 0.001%

    No Known Activations