© 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. 30549
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    egah
    -0.09
    ersch
    -0.08
    artz
    -0.08
    ensch
    -0.08
    iaga
    -0.07
    à¥ĩम
    -0.07
    ãĤ¤ãĥ«
    -0.07
    ettino
    -0.07
    ucus
    -0.07
    æĹłæŀģ
    -0.07
    POSITIVE LOGITS
    ulf
    0.07
    ä¸įåİĮ
    0.07
    rna
    0.07
    fes
    0.07
    uke
    0.06
    æķ£
    0.06
    ais
    0.06
    plast
    0.06
    ul
    0.06
    çīĪæĿĥå½Ĵ
    0.06
    Activations Density 0.012%

    No Known Activations