© 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. 51488
    Prev
    Next
    INDEX
    Explanations

    place names with endings

    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
    ï¸ı
    -0.10
    Ø©
    -0.09
    etas
    -0.09
    ulli
    -0.08
    ourg
    -0.08
    ction
    -0.08
    ation
    -0.08
    á»±u
    -0.08
    ะ
    -0.08
    ända
    -0.08
    POSITIVE LOGITS
    bourne
    0.07
    µ
    0.07
    ãģ¹ãģį
    0.07
    inz
    0.07
    ç¢ī
    0.07
    oretical
    0.06
    ippers
    0.06
    ienst
    0.06
    à¹īà¸Ļ
    0.06
    ä¸įè¦ģ太
    0.06
    Activations Density 0.001%

    No Known Activations