© 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. 39332
    Prev
    Next
    INDEX
    Explanations

    clear: floats or states

    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
    女éĥİ
    -0.09
    yssey
    -0.09
    oodoo
    -0.08
    uju
    -0.08
    agon
    -0.08
    celli
    -0.08
    agonal
    -0.08
    uristic
    -0.08
    å©¿
    -0.08
    ISIBLE
    -0.08
    POSITIVE LOGITS
     rÃłng
    0.09
    liness
    0.09
    bie
    0.08
     rá»ĩt
    0.08
    ness
    0.08
    ERENCE
    0.08
    avanaugh
    0.07
    -cut
    0.07
    urent
    0.07
    à¹Ĩ
    0.07
    Activations Density 0.037%

    No Known Activations