© 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. 50954
    Prev
    Next
    INDEX
    Explanations

    largest, biggest, greatest, highest, max

    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
    lette
    -0.08
    iat
    -0.08
    heim
    -0.07
    acco
    -0.07
    å³»
    -0.07
    ÅĽ
    -0.07
     Gru
    -0.07
    .consume
    -0.07
    inh
    -0.07
    å¤ĦçIJĨ好
    -0.06
    POSITIVE LOGITS
     extent
    0.07
    .max
    0.07
     safely
    0.07
    èİ«è¿ĩäºİ
    0.07
    ãģ¾ãģ§
    0.07
    èĥĨåŃIJ
    0.07
    ä¸įèĥ½è¶ħè¿ĩ
    0.07
    æĺ¯æľĢ大çļĦ
    0.07
    (Max
    0.07
     extents
    0.07
    Activations Density 0.019%

    No Known Activations