© 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. 34957
    Prev
    Next
    INDEX
    Explanations

    pivot and pivotal terms

    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
    odore
    -0.08
    ieder
    -0.08
    liness
    -0.07
    cape
    -0.07
    oret
    -0.07
    erge
    -0.07
    æĦ§
    -0.07
    ewolf
    -0.07
    cript
    -0.07
    ä½³èĤ´
    -0.07
    POSITIVE LOGITS
    aré
    0.08
    ¢
    0.08
    estu
    0.08
    Į
    0.08
    teles
    0.08
    maat
    0.08
    rary
    0.07
    atriz
    0.07
    ainless
    0.07
    доб
    0.07
    Activations Density 0.020%

    No Known Activations