© 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. 11062
    Prev
    Next
    INDEX
    Explanations

    not the same thing

    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
    å¿ĥçľ¼
    -0.07
    ä¸įæĺ¯å¾Ī
    -0.07
     Unsure
    -0.07
    å¦Ĥæŀľä¸įèĥ½
    -0.07
    ÑĪок
    -0.07
     partially
    -0.07
    ä½Ĩæĺ¯çĶ±äºİ
    -0.06
    æĹłæĺİæĺ¾
    -0.06
    æ¸IJ
    -0.06
    ä¸įå¤ĸ
    -0.06
    POSITIVE LOGITS
     separate
    0.16
     Separate
    0.15
     seperate
    0.15
     separado
    0.14
     separ
    0.13
    æĺ¯ä¸įåIJĮçļĦ
    0.13
    Separ
    0.13
     separately
    0.13
     unrelated
    0.13
     distinct
    0.13
    Activations Density 0.081%

    No Known Activations