© 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. 46788
    Prev
    Next
    INDEX
    Explanations

    ли, ãģĭ, åIJĹ

    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
    ingham
    -0.10
    اÙĭ
    -0.10
    à¸Ļà¸Ļ
    -0.10
    ãĥ£
    -0.10
    ONUS
    -0.09
    aire
    -0.09
    ments
    -0.09
    à¸Ļาà¸Ļ
    -0.09
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    -0.09
    mates
    -0.08
    POSITIVE LOGITS
    zuf
    0.09
    soever
    0.08
    Ùĩ
    0.07
    wel
    0.06
    forme
    0.06
    åķ¡
    0.06
    è¾Ī
    0.06
    quel
    0.06
    ÙijÙĩ
    0.06
    สà¹Į
    0.06
    Activations Density 0.001%

    No Known Activations