© 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. 38834
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
     âĢ¦
    -0.10
    âĢ¦
    -0.09
    -0.09
     “
    -0.08
    ,
    -0.08
    ä¹ĭç±»
    -0.08
    -0.07
    åĪ©äºİ
    -0.07
    “
    -0.06
    ainless
    -0.06
    POSITIVE LOGITS
    å¤ļåIJĥä¸ĢäºĽ
    0.09
    éĺħè¯»æľ¬æĸĩ
    0.08
     hardcoded
    0.08
    以赴
    0.08
    塵
    0.08
     letzt
    0.08
    å¸ĮæľĽåı¯ä»¥å¸®åĬ©
    0.08
    otin
    0.08
    )const
    0.08
    allon
    0.08
    Activations Density 0.001%

    No Known Activations