© 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. 27305
    Prev
    Next
    INDEX
    Explanations

    interface or type names

    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
    ám
    -0.07
    Reducers
    -0.07
    pong
    -0.07
    太éĥİ
    -0.07
    ÐŁÐ£
    -0.07
    èģ
    -0.06
    chini
    -0.06
    èĩªè¨Ģ
    -0.06
    #endregion
    -0.06
    ahu
    -0.06
    POSITIVE LOGITS
    å¾·åįİ
    0.08
    bauer
    0.07
    人ä¹ĭ
    0.07
    erness
    0.07
     STOCK
    0.07
    schau
    0.07
    ูà¹ī
    0.06
    æĪĸå¤ļ个
    0.06
    裳
    0.06
    æĪĸå¤ļ
    0.06
    Activations Density 0.198%

    No Known Activations