© 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. 25459
    Prev
    Next
    INDEX
    Explanations

    of the state

    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
    elm
    -0.07
    ecat
    -0.06
    æľ¬çıŃ
    -0.06
    ovsky
    -0.06
    æĮºèĥ¸
    -0.06
    å·§
    -0.06
    çIJĥèĽĭçĻ½
    -0.06
     rit
    -0.06
    ekar
    -0.06
    acqu
    -0.06
    POSITIVE LOGITS
     malas
    0.08
    èĶĵ
    0.08
    ç©·
    0.08
    éĩĬ
    0.08
    .cp
    0.08
    å°ĺ
    0.08
    å®ŀä¸ļ
    0.07
    inste
    0.07
     quaran
    0.07
    osh
    0.07
    Activations Density 0.001%

    No Known Activations