© 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. 43950
    Prev
    Next
    INDEX
    Explanations

    questions about what happens

    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
    亦çĦ¶
    -0.07
     Dalle
    -0.07
     others
    -0.06
    `.
    -0.06
     theirs
    -0.06
     ÑĤоже
    -0.06
    缸åºĶ
    -0.06
    åĬª
    -0.06
    èĩ³äºİ
    -0.06
    åħ¶ä»ĸ
    -0.06
    POSITIVE LOGITS
    ãĢįãĢģãĢĮ
    0.11
    )ãĢģ
    0.10
    ï¼īãĢģ
    0.10
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.09
    ãĢįãĢĮ
    0.09
    ä¸Ģæĺ¯è¦ģ
    0.09
    ä¸Ģæĺ¯
    0.08
    ãĢıãĢİ
    0.08
    以ä¸ĭåĩłä¸ª
    0.08
    ãĢįãĢģ
    0.08
    Activations Density 0.205%

    No Known Activations