© 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. 25869
    Prev
    Next
    INDEX
    Explanations

    analyses

    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
    stype
    -0.07
     ΤοÏħ
    -0.07
    à¯įத
    -0.07
    redd
    -0.07
    äºĨåĩłåĪĨ
    -0.07
    åĩłåĪĨ
    -0.06
    ä¸ĢéĿ¢
    -0.06
    anness
    -0.06
    å¼Ĥèĥ½
    -0.06
     orderby
    -0.06
    POSITIVE LOGITS
    len
    0.08
    ä¿IJ
    0.08
    illons
    0.07
    nad
    0.07
    nbsp
    0.07
    ung
    0.07
    etus
    0.07
    rina
    0.07
    eros
    0.06
    æĬĬå·¥ä½ľ
    0.06
    Activations Density 0.013%

    No Known Activations