© 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. 38543
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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
    åľ¨æīĢ
    -0.08
    å¤ĸéľ²
    -0.08
    å¦Ĥæ¶īåıĬ
    -0.07
    <tool_response>
    -0.07
    æ¡£
    -0.07
     Rad
    -0.07
    -rad
    -0.07
     Newest
    -0.07
    Rad
    -0.07
    xba
    -0.07
    POSITIVE LOGITS
    å®ĮäºĨ
    0.07
    åĪ©çļĦ
    0.07
    æĪIJç«ĭ
    0.07
    æĪIJç«ĭçļĦ
    0.07
     waarbij
    0.07
    odos
    0.06
    æķĪçİĩé«ĺ
    0.06
    à¸Ĺีà¹Īà¹Ģà¸ģิà¸Ķà¸Ĥึà¹īà¸Ļ
    0.06
    inach
    0.06
    abbrev
    0.06
    Activations Density 0.014%

    No Known Activations