© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17993
    Prev
    Next
    INDEX
    Explanations

    matrix indices

    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
    åħ¶ä¸Ĭ
    -0.07
    å¿ħåħĪ
    -0.07
    ogli
    -0.07
    éģĵéģĵ
    -0.06
    ÙĪÙĨات
    -0.06
    :\/\/
    -0.06
    ä¸įéĢĤ
    -0.06
    .newBuilder
    -0.06
    好åѦçĶŁ
    -0.06
    ä½ľä¸º
    -0.06
    POSITIVE LOGITS
    CDATA
    0.07
    éĺ¶
    0.07
    plier
    0.07
    klin
    0.07
    ä»ĸ便
    0.07
    opter
    0.07
    è²ī
    0.07
    åĴĮä¸ĭ
    0.07
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.07
    rund
    0.07
    Activations Density 0.006%

    No Known Activations