© 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. 21316
    Prev
    Next
    INDEX
    Explanations

    Longford

    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
    ç¼
    -0.07
    ..
    -0.07
    çĻ½çļĦ
    -0.07
    姿
    -0.06
     jun
    -0.06
    éĹ®ä»ĸ
    -0.06
    endant
    -0.06
    quire
    -0.06
    éĹ
    -0.06
    .datasets
    -0.06
    POSITIVE LOGITS
    ابÙĬ
    0.08
    ายà¸Ļ
    0.07
    好èĩªå·±çļĦ
    0.07
    à¸Ĺà¸ĺ
    0.07
    Ñħан
    0.07
    Ùĩد
    0.07
    oxy
    0.07
    å·²äºİ
    0.07
    agan
    0.07
    çĴĢ
    0.07
    Activations Density 0.001%

    No Known Activations