© 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. 62773
    Prev
    Next
    INDEX
    Explanations

    only

    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
    ä¸įå¿ħè¦ģ
    -0.08
    olec
    -0.08
    arine
    -0.08
    èĻ½å°ı
    -0.08
    èĻ½çĦ¶ä¸įæĺ¯
    -0.08
    umon
    -0.08
    èĻ½çĦ¶æ²¡æľī
    -0.08
    same
    -0.08
    ä¸įèĻļ
    -0.07
    ä¸įå¿ħ
    -0.07
    POSITIVE LOGITS
    ä»ħ代表
    0.11
     лиÑĪÑĮ
    0.10
     Ùħجرد
    0.10
    ä»ħæıIJä¾Ľ
    0.09
     merely
    0.09
     jedynie
    0.08
    ä»ħä½ľ
    0.08
     mere
    0.08
    ä»ħä¾Ľ
    0.08
    èĢĮå·²
    0.08
    Activations Density 0.161%

    No Known Activations