© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55258
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ạp
    -0.08
    lector
    -0.07
    ÐľÐŁ
    -0.07
    ä½Ĩæĺ¯è¿Ļ个
    -0.07
    åįģåħ«
    -0.07
    æŁ¥
    -0.07
    inqui
    -0.07
    åįĹ岸
    -0.07
    landen
    -0.07
    è®°èĢħäºĨ解åĪ°
    -0.07
    POSITIVE LOGITS
    éĢĬ
    0.07
    ByKey
    0.07
    &nbsp
    0.07
    çħ¦
    0.07
     (&
    0.06
    çĪ±åĽ½ä¸»ä¹ī
    0.06
    اء
    0.06
    ButtonClick
    0.06
    elly
    0.06
    ç§ijåѦæĢ§
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.