© 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. 13660
    Prev
    Next
    INDEX
    Explanations

    equation or list item numbers

    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
    hver
    -0.09
    hei
    -0.08
    ibaldi
    -0.08
    ascus
    -0.08
    ä¸ĩ平米
    -0.08
    åħ¬åı¸èij£äºĭéķ¿
    -0.08
     Galler
    -0.08
    oug
    -0.08
    iams
    -0.08
     депÑĥÑĤа
    -0.07
    POSITIVE LOGITS
    uve
    0.06
    ายà¸Ļ
    0.06
     infra
    0.06
    umat
    0.06
     re
    0.06
     imb
    0.06
     pull
    0.05
    ×Ļר×Ķ
    0.05
    ãĤ¸ãĥ§
    0.05
    ç¾İ
    0.05
    Activations Density 0.101%

    No Known Activations