© 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. 27765
    Prev
    Next
    INDEX
    Explanations

    file type extensions and string formats

    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
    Abb
    -0.08
    æĬĺ
    -0.07
    abol
    -0.07
    çĶ¥
    -0.07
    _PRIORITY
    -0.07
    upon
    -0.07
    umph
    -0.07
    çĭ®
    -0.07
    å¼¥
    -0.06
    鸣
    -0.06
    POSITIVE LOGITS
     ranged
    0.08
    Ñģпи
    0.08
    èĮĥåĽ´ä¸º
    0.08
     ranges
    0.07
    неÑĤа
    0.07
    (range
    0.07
    spin
    0.07
     range
    0.07
     Ai
    0.07
    æľĢå¤ļ
    0.07
    Activations Density 0.005%

    No Known Activations