© 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. 50919
    Prev
    Next
    INDEX
    Explanations

    Precision, tiny, almost, practically

    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
    å²IJ
    -0.08
    åk
    -0.07
    åŃļ
    -0.07
    DAH
    -0.07
    æ¸Īãģ¿
    -0.07
    ROTO
    -0.07
    rouch
    -0.07
    åĽĽåħŃ级
    -0.07
    åĬłåĢį
    -0.07
    DateFormat
    -0.07
    POSITIVE LOGITS
    æİ¥è¿ij
    0.09
    åĩłä¹İ
    0.08
    Precision
    0.08
     tiny
    0.07
    åĩłä¹İæĺ¯
    0.07
    å¹¾ä¹İ
    0.07
     almost
    0.07
    Tiny
    0.07
     practically
    0.07
     Tiny
    0.07
    Activations Density 0.004%

    No Known Activations