© 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. 16899
    Prev
    Next
    INDEX
    Explanations

    import statements

    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¿Ń
    -0.08
    -plugins
    -0.07
    æĪIJé¾Ļ
    -0.07
    ä¸Ģç¬Ķ
    -0.06
    å°Ķçī¹
    -0.06
    iros
    -0.06
     targetType
    -0.06
    大åħ³
    -0.06
    人马
    -0.06
     CURLOPT
    -0.06
    POSITIVE LOGITS
    Åľ
    0.08
    éĺħè¯»æľ¬æĸĩåīį
    0.08
    èĥ½ä»İ
    0.08
    å·²ç»ıä»İ
    0.08
    EGO
    0.08
    from
    0.08
    Ñħема
    0.08
    ])/
    0.08
    对æѤä¸įæī¿æĭħä»»ä½ķ
    0.08
    èĢĮä»İ
    0.08
    Activations Density 0.094%

    No Known Activations