© 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. 8111
    Prev
    Next
    INDEX
    Explanations

    parsing structured data

    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
     saud
    -0.08
    strup
    -0.07
    uddle
    -0.07
     latter
    -0.07
    æĺ¯åĶ¯ä¸Ģ
    -0.07
    reau
    -0.06
    äºĨäºĭ
    -0.06
    éĺħè¯»æľ¬æĸĩåīį
    -0.06
    ع
    -0.06
    ีà¹Ĥà¸Ń
    -0.06
    POSITIVE LOGITS
    رز
    0.08
    ιδ
    0.07
    ebr
    0.07
    óst
    0.07
    isiones
    0.07
    nement
    0.07
    eut
    0.07
    ÑĤÑĢо
    0.07
    igni
    0.07
    PARSE
    0.07
    Activations Density 0.054%

    No Known Activations