© 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. 60529
    Prev
    Next
    INDEX
    Explanations

    packing analysis

    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
    apur
    -0.07
    ornado
    -0.07
    åİŁä»¶åıĬ
    -0.07
    гÑĢад
    -0.07
    Scaler
    -0.07
     sever
    -0.07
    onti
    -0.07
     klimat
    -0.07
    _DEFINE
    -0.07
    Ùĩاب
    -0.07
    POSITIVE LOGITS
     arrangement
    0.10
    æİĴåĪĹ
    0.10
     packing
    0.09
    ç´§å¯Ĩ
    0.09
    åįłæľīçİĩ
    0.08
    errer
    0.08
     arrangements
    0.08
    packing
    0.08
    éļĻ
    0.08
     arranged
    0.08
    Activations Density 0.010%

    No Known Activations