© 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. 61719
    Prev
    Next
    INDEX
    Explanations

    the single

    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
    Č↵
    -0.07
    éĻ¤äºĨ
    -0.07
    æĸ°çļĦä¸Ģ
    -0.07
    ä¸įåIJĮçļĦ
    -0.07
    æ¯Ķ为
    -0.07
     infatti
    -0.07
     totiž
    -0.06
     as
    -0.06
     عÙĦاÙĪÙĩ
    -0.06
     namelijk
    -0.06
    POSITIVE LOGITS
     ones
    0.14
     others
    0.13
    ãģĿãģĨãģ§
    0.12
     lainnya
    0.12
    others
    0.11
    ä»»ä½ķåħ¶ä»ĸ
    0.10
    ັàºĻ
    0.10
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.10
    Others
    0.10
     theirs
    0.10
    Activations Density 0.219%

    No Known Activations