© 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. 4662
    Prev
    Next
    INDEX
    Explanations

    legal matters or consultation

    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
    hood
    -0.07
    eldon
    -0.07
    ellite
    -0.07
    ìĹ´
    -0.07
    нами
    -0.07
    elper
    -0.07
    ete
    -0.06
    вим
    -0.06
    ο
    -0.06
    eting
    -0.06
    POSITIVE LOGITS
    ousy
    0.09
    istically
    0.09
    mente
    0.09
    izable
    0.09
    izat
    0.09
    izing
    0.09
    aily
    0.08
    ¸
    0.08
    umbre
    0.08
    geries
    0.08
    Activations Density 0.010%

    No Known Activations