© 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. 6943
    Prev
    Next
    INDEX
    Explanations

    I or we followed by verb

    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
    ness
    -0.12
    mente
    -0.08
    ingly
    -0.08
    ment
    -0.08
    اÙĭ
    -0.07
    apult
    -0.07
    antly
    -0.07
    Ùħر
    -0.07
    pun
    -0.07
    از
    -0.07
    POSITIVE LOGITS
    'll
    0.13
    ’ll
    0.12
    bsites
    0.12
    've
    0.11
    're
    0.10
    aning
    0.10
    ’ve
    0.10
    bservice
    0.10
     ourselves
    0.10
    ’re
    0.09
    Activations Density 0.988%

    No Known Activations