© 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. 22045
    Prev
    Next
    INDEX
    Explanations

    parenthetical numbers and positions

    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¸įéĢĢ
    -0.06
    åĢ¦
    -0.06
    æĬ¹
    -0.06
    encil
    -0.06
    å®ļåŀĭ
    -0.06
    æīĢéľĢè¦ģçļĦ
    -0.06
    .Persistence
    -0.06
    å¤ļäºİ
    -0.06
    beck
    -0.06
    elman
    -0.06
    POSITIVE LOGITS
     kolej
    0.08
     positions
    0.07
    unca
    0.07
    _refer
    0.07
     numbered
    0.07
    æľīæĸĻ
    0.07
    äºĶåij³
    0.07
     cal
    0.07
     Büy
    0.07
    yms
    0.07
    Activations Density 0.003%

    No Known Activations