© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49929
    Prev
    Next
    INDEX
    Explanations

    moving away from

    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
    ä¸įè¡°
    -0.09
    oup
    -0.08
    ogy
    -0.08
    chor
    -0.08
    eru
    -0.07
    รà¸Ńย
    -0.07
    .extensions
    -0.07
    QUIRE
    -0.07
    à¥Įर
    -0.07
    IER
    -0.07
    POSITIVE LOGITS
     khá»ıi
    0.21
    å¤ªè¿ľ
    0.09
     away
    0.09
    离
    0.09
     лиÑĪ
    0.08
    åļ£
    0.08
    à¸Ńà¸Ńà¸ģà¸Īาà¸ģ
    0.08
    è¿ľç¦»
    0.08
     from
    0.08
    éĽ¢
    0.08
    Activations Density 0.211%

    No Known Activations