© 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. 13654
    Prev
    Next
    INDEX
    Explanations

    data tracking and record-keeping

    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
    åIJ»
    -0.08
    apus
    -0.07
    áter
    -0.07
    åı®
    -0.06
    å¨ģåĬĽ
    -0.06
    ä¸Ģåı£
    -0.06
     sizes
    -0.06
    æĸ½å±ķ
    -0.06
     eup
    -0.06
    arged
    -0.06
    POSITIVE LOGITS
    è¿ĻæĿ¡
    0.08
    éĢĻæ¢Ŀ
    0.08
    轨迹
    0.08
    emma
    0.08
    تاÙĨ
    0.07
     непÑĢеÑĢÑĭв
    0.07
    解æĥij
    0.07
    sWith
    0.07
     continuity
    0.07
    è¿ŀç»ŃæĢ§
    0.07
    Activations Density 0.001%

    No Known Activations