© 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. 59829
    Prev
    Next
    INDEX
    Explanations

    plural nouns followed by verbs or conjunctions

    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
     orth
    -0.06
    åĽŀå¤į
    -0.05
    èĴĻå¾·
    -0.05
    DM
    -0.05
    HM
    -0.05
    aura
    -0.05
     t
    -0.05
     sk
    -0.05
    unc
    -0.05
    elm
    -0.05
    POSITIVE LOGITS
    uris
    0.09
    irting
    0.09
    isle
    0.08
    leneck
    0.08
    æģ¤
    0.08
    大åѦéĻ¢
    0.08
    leston
    0.08
    anita
    0.08
    شار
    0.08
    blr
    0.08
    Activations Density 0.231%

    No Known Activations