© 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. 32163
    Prev
    Next
    INDEX
    Explanations

    preprocessed version

    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
    ero
    -0.08
     –
    -0.06
     Lat
    -0.06
    æŁ¥
    -0.06
    lat
    -0.06
    ...
    -0.06
    âĢ¦
    -0.06
    çİĭå¿Ĺ
    -0.06
    计æıIJ
    -0.06
    æĵį纵
    -0.06
    POSITIVE LOGITS
    Indent
    0.09
    åħ¨æĿij
    0.09
    -indent
    0.09
    ä¸įæĥĬ
    0.08
    _indent
    0.08
    åħ¨å¥Ĺ
    0.08
     preceded
    0.08
    fonds
    0.08
    WithIdentifier
    0.08
    ÙĪÙĨØ©
    0.08
    Activations Density 0.008%

    No Known Activations