© 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. 40861
    Prev
    Next
    INDEX
    Explanations

    definition, version, quantity, effects

    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
    ç´§å¼łçļĦ
    -0.08
    ä¸Ģ个æĸ°
    -0.07
    jol
    -0.07
    гое
    -0.07
    (Of
    -0.07
    onos
    -0.07
    andas
    -0.07
    ä¸Ģåľº
    -0.07
    -cols
    -0.07
    -FIRST
    -0.07
    POSITIVE LOGITS
    åı¯
    0.08
    สำà¸Ħัà¸įà¸Ĥà¸Ńà¸ĩ
    0.08
    enze
    0.07
     de
    0.07
    å®ļçĦ¶
    0.07
    %",
    0.07
    ÙĩاÛĮ
    0.07
    opsis
    0.07
    à¹Ģà¸īà¸ŀาะ
    0.07
    หà¸Ļึà¹Īà¸ĩà¸Ĥà¸Ńà¸ĩ
    0.07
    Activations Density 0.045%

    No Known Activations