© 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. 40416
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

    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
    ä¸Ģæ³¢
    -0.09
    è¿ĩå±±
    -0.09
     asal
    -0.08
    rones
    -0.08
    nacz
    -0.08
     somehow
    -0.08
    ÙĪÙĨا
    -0.08
    ä¸Ģä¼Ĺ
    -0.08
    -tabs
    -0.08
     goodies
    -0.08
    POSITIVE LOGITS
     ('
    0.07
     reconstructed
    0.06
     (*
    0.06
    ofer
    0.06
     ("
    0.06
    (({
    0.06
     approximately
    0.06
     ($(
    0.06
    imir
    0.06
     Arb
    0.06
    Activations Density 0.233%

    No Known Activations