© 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. 47682
    Prev
    Next
    INDEX
    Explanations

    automatically or spontaneously

    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¸įæŃ»
    -0.07
    egel
    -0.07
     articul
    -0.07
    à¸ķิà¸Ļ
    -0.07
    ä¸įå¼ĥ
    -0.07
    tuv
    -0.07
    prat
    -0.07
    egi
    -0.07
    ouri
    -0.07
    å¹²ç»ĥ
    -0.07
    POSITIVE LOGITS
     automatic
    0.24
    èĩªåĬ¨
    0.24
    automatic
    0.22
    Automatic
    0.22
     Automatic
    0.22
     automatically
    0.21
     spontaneous
    0.20
    èĩªåĬ¨çĶŁæĪIJ
    0.20
     automatica
    0.20
     Automatically
    0.19
    Activations Density 0.451%

    No Known Activations