© 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. 44130
    Prev
    Next
    INDEX
    Explanations

    weight loss, weightlessness, weight reduction

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ê¹IJ
    -0.10
    端åĢª
    -0.08
    Leggi
    -0.08
    ussion
    -0.08
    ryption
    -0.08
    ذاÙĥ
    -0.08
    stras
    -0.08
    Referensi
    -0.07
    plin
    -0.07
     módon
    -0.07
    POSITIVE LOGITS
    lessness
    0.11
    fully
    0.09
    iness
    0.09
    fulness
    0.09
    eds
    0.08
    ihan
    0.08
    ings
    0.08
    lessly
    0.08
    less
    0.08
    cloak
    0.08
    Activations Density 0.025%

    No Known Activations