© 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. 43643
    Prev
    Next
    INDEX
    Explanations

    dry weight or mass percentage

    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
     zeit
    -0.07
     pair
    -0.07
    åįĬå¾Ħ
    -0.07
    æĦŁæŁĵèĢħ
    -0.07
    èį¨
    -0.07
    秩
    -0.07
    åĥļ
    -0.07
    æºĿ
    -0.06
    å§ĭç¥ĸ
    -0.06
    è¯ķæİ¢
    -0.06
    POSITIVE LOGITS
    éĩįéĩı
    0.09
    Recovered
    0.09
    ç»ĵæŀĦä¸Ń
    0.09
     lean
    0.09
    çļĦéĩįéĩı
    0.09
    æ¯Ķéĩį
    0.08
    æ°´åĪĨ
    0.08
    percentage
    0.08
    ç»ĦæĪIJ
    0.08
    çļĦæ¯Ķéĩį
    0.08
    Activations Density 0.084%

    No Known Activations