© 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. 17115
    Prev
    Next
    INDEX
    Explanations

    str followed by ace or parenthesis/equals

    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
    ़
    -0.12
    áĥ£áĥłáĥĺ
    -0.11
    lesh
    -0.10
    ਼
    -0.09
    stry
    -0.09
    à¯į
    -0.08
    àµį
    -0.08
    à³į
    -0.08
    ়
    -0.08
    تÙħاد
    -0.08
    POSITIVE LOGITS
    Åijl
    0.10
    scher
    0.09
    schild
    0.09
    s
    0.09
    sic
    0.09
    à¸Ļาà¸Ļ
    0.08
    à¸Ļา
    0.08
    anoia
    0.08
     vá»±ng
    0.08
    ively
    0.08
    Activations Density 0.082%

    No Known Activations