© 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. 44340
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by specifics

    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
    ingk
    -0.07
    зади
    -0.07
    scheid
    -0.07
    tte
    -0.07
    ingin
    -0.07
    ingue
    -0.07
    kow
    -0.07
    rite
    -0.06
    atorial
    -0.06
    ingg
    -0.06
    POSITIVE LOGITS
     whom
    0.09
     cioè
    0.08
    æ¯Ķå¦Ĥ说
    0.08
    á»ģm
    0.07
     particular
    0.07
    oretical
    0.07
    NST
    0.07
    Isl
    0.07
    ÑģÑı
    0.07
    out
    0.07
    Activations Density 0.164%

    No Known Activations