© 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. 8731
    Prev
    Next
    INDEX
    Explanations

    and or separators

    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
    åłĤ
    -0.06
    yre
    -0.06
    Âł
    -0.06
    esting
    -0.06
     âĢŀ
    -0.06
    [
    -0.06
    ire
    -0.06
    env
    -0.06
    éĽĦ
    -0.06
     “
    -0.05
    POSITIVE LOGITS
    ãĥªãĤ¨
    0.08
    apul
    0.08
     기íĥĢ
    0.08
    धा
    0.08
    رÛĮاÙĨ
    0.08
    ãĥĥãĤ«
    0.08
    evin
    0.07
    ÑģлÑĥж
    0.07
    ãĥ³ãĥĹ
    0.07
     autres
    0.07
    Activations Density 0.095%

    No Known Activations