© 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. 47904
    Prev
    Next
    INDEX
    Explanations

    summary or report

    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
    annya
    -0.08
    çĦ¶åIJİå°Ĩ
    -0.08
    åĭĴæĸ¯
    -0.08
    ervi
    -0.08
    argin
    -0.07
    ervo
    -0.07
    ä¿Ŀè¯ģåħ¶
    -0.07
    è¿ĺæľīçĤ¹
    -0.07
    ä¸Ģ缮
    -0.07
    ãģĿãģĨãģ§
    -0.07
    POSITIVE LOGITS
    综ä¸ĬæīĢè¿°
    0.09
    綾
    0.08
    ä¸įæĺ¯ä¸Ģ个
    0.08
    éĢļè¿ĩåĪĨæŀIJ
    0.07
    éĢļè¿ĩ对
    0.07
    éĢļè¿ĩ以ä¸Ĭ
    0.07
    assistant
    0.07
    ioni
    0.07
    羣çIJĨ
    0.06
    æľ¬çĿĢ
    0.06
    Activations Density 0.018%

    No Known Activations