© 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. 30386
    Prev
    Next
    INDEX
    Explanations

    list elements or list-related elements

    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
    igy
    -0.08
    Normals
    -0.07
    wege
    -0.07
    пÑĮ
    -0.07
    вÑĮ
    -0.07
    itti
    -0.07
    ÒĵÑĭ
    -0.07
    è¶Ł
    -0.07
     saja
    -0.06
     precis
    -0.06
    POSITIVE LOGITS
    asurer
    0.07
    tribu
    0.07
    emics
    0.07
    dbo
    0.07
    bem
    0.07
    utters
    0.07
    éĤ£ä¹Īå¤ļ
    0.06
    娥
    0.06
    æķ°åįģå¹´
    0.06
    å¤ļå¾Ĺ
    0.06
    Activations Density 0.050%

    No Known Activations