© 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. 12563
    Prev
    Next
    INDEX
    Explanations

    sender name, mast cells, hairpin, sporting history, indexing principles

    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
    ìłģìľ¼ë¡ľ
    -0.08
    oriously
    -0.07
    olutely
    -0.07
     inherently
    -0.06
     importantly
    -0.06
     themselves
    -0.06
    ège
    -0.06
    è¿Ļ个æĺ¯
    -0.06
    éĢļ常æĥħåĨµä¸ĭ
    -0.06
     newly
    -0.06
    POSITIVE LOGITS
    ahn
    0.08
    -to
    0.07
    anja
    0.07
    angka
    0.07
    ehan
    0.07
    hani
    0.07
    hurst
    0.07
    imana
    0.07
    å·¥ä½ľä¼ļè®®
    0.07
    лÑıÑĤ
    0.07
    Activations Density 1.318%

    No Known Activations