© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51971
    Prev
    Next
    INDEX
    Explanations

    individual / unit concepts

    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
    Negative Logits
    umin
    -0.07
    éħ¸è¾£
    -0.07
    akers
    -0.07
    l
    -0.06
    umar
    -0.06
    æ±²
    -0.06
    æľĿåIJij
    -0.06
    æİ
    -0.06
    æľŁä¸Ń
    -0.06
    b
    -0.06
    POSITIVE LOGITS
    个ä½ĵ
    0.09
    utzer
    0.09
     individually
    0.09
    izzi
    0.09
     indywidual
    0.09
    åĢĭåĪ¥
    0.08
    iach
    0.08
    个åĪ«
    0.08
     individuel
    0.08
    cntl
    0.08
    Activations Density 0.008%

    No Known Activations