© 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. 55013
    Prev
    Next
    INDEX
    Explanations

    verbs related to process and action

    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
    xac
    -0.08
    ezz
    -0.07
    åľ¨åģļ
    -0.07
    èī¯å¤ļ
    -0.07
    leh
    -0.07
    aglio
    -0.07
    å¾Ī好çļĦ
    -0.07
    çĿĢçļĦ
    -0.07
    客çļĦ
    -0.07
    processors
    -0.06
    POSITIVE LOGITS
    Specifier
    0.08
     accordingly
    0.08
    utan
    0.07
    à¹Ħà¸Ķà¹īà¹Ģลย
    0.07
     pit
    0.07
    auta
    0.07
    utherford
    0.06
    就好äºĨ
    0.06
     inaugural
    0.06
     enfin
    0.06
    Activations Density 0.227%

    No Known Activations