© 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. 23778
    Prev
    Next
    INDEX
    Explanations

    introduces an explanation or follows a statement

    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
    éĥ½åºĶ该
    -0.08
    éĥ½ä¸įæĥ³
    -0.08
    éĥ½æľīèĩªå·±çļĦ
    -0.08
    å¿ĥçĶ°
    -0.07
    mans
    -0.07
    大å¹ħ度
    -0.07
    éĥ½æ¯Ķ
    -0.07
    ë²Į
    -0.07
    éĥ½èĥ½å¤Ł
    -0.07
    éĥ½ä¸įèĥ½
    -0.07
    POSITIVE LOGITS
    å·¥ä½ľé¡ºåĪ©
    0.08
    èĩ³æѤ
    0.07
    æĪIJç«ĭ
    0.07
    à¹ĥà¸Ĭà¹īà¹Ħà¸Ķà¹ī
    0.07
    вÑĭÑĪе
    0.07
     align
    0.07
     holds
    0.07
     above
    0.07
    uff
    0.07
     applies
    0.07
    Activations Density 0.010%

    No Known Activations