© 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. 27163
    Prev
    Next
    INDEX
    Explanations

    quotation marks, URLs, code

    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
    Âł
    -0.10
     –
    -0.09
     Âł
    -0.08
     Âł Âł
    -0.07
     Âł Âł Âł Âł
    -0.07
     âĢ¦
    -0.07
    ãn
    -0.07
    æ¯
    -0.06
    秫
    -0.06
    asio
    -0.06
    POSITIVE LOGITS
    agak
    0.08
    ongan
    0.08
    uš
    0.08
     $"
    0.08
    âĸł
    0.08
    itional
    0.08
    obao
    0.08
    æİĮä¸Ĭ
    0.08
    obook
    0.08
    ãĥ¡ãĥªãĤ«
    0.08
    Activations Density 0.324%

    No Known Activations