© 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. 7014
    Prev
    Next
    INDEX
    Explanations

    punctuation and 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
    ibal
    -0.09
    çµ®
    -0.09
    ÑĢак
    -0.08
    erva
    -0.08
    icola
    -0.08
    èIJ©
    -0.07
     bienvenus
    -0.07
    allar
    -0.07
    zicht
    -0.07
    ITAL
    -0.07
    POSITIVE LOGITS
    ä½ķåĨµ
    0.07
    ck
    0.07
    um
    0.07
    åºĶçĶ¨åĪ°
    0.07
     Shelby
    0.06
    éļĶ
    0.06
    Äħż
    0.06
    å±¹
    0.06
     splend
    0.06
    Bio
    0.06
    Activations Density 0.039%

    No Known Activations