© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30255
    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
    dddd
    -0.09
    herits
    -0.09
    etine
    -0.09
    elui
    -0.09
    eware
    -0.08
    ÅĻed
    -0.08
    碼
    -0.08
    ächt
    -0.08
    å°ĶèĴĻ
    -0.08
    .Regular
    -0.08
    POSITIVE LOGITS
     behalf
    0.08
    oro
    0.06
    çĩ
    0.06
    รà¸ģ
    0.06
    éĢļ天
    0.06
     matching
    0.06
    erna
    0.06
    atta
    0.06
    æľī人
    0.06
    oria
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.