© 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. 19635
    Prev
    Next
    INDEX
    Explanations

    this study

    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
    LA
    -0.07
    æĸŃ
    -0.07
    ound
    -0.06
     Polis
    -0.06
    à¸Ħà¸ĵะ
    -0.06
    大æĭĩæĮĩ
    -0.06
    θÏħ
    -0.06
    å¤ļ大
    -0.06
     ëĭ¨
    -0.06
    å¼ıä¸Ń
    -0.06
    POSITIVE LOGITS
    غÙĦ
    0.08
    aranya
    0.08
    hein
    0.08
    ertino
    0.08
    ÙĪدÛĮ
    0.08
    armo
    0.07
    @example
    0.07
    cliffe
    0.07
    hton
    0.07
    elloworld
    0.07
    Activations Density 0.001%

    No Known Activations