© 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. 4603
    Prev
    Next
    INDEX
    Explanations

    molecular size, weight, and fragments

    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
    å»ī
    -0.08
    åľ¨ä½ı
    -0.07
    issan
    -0.07
    åµĮåħ¥å¼ı
    -0.07
    éĽħ
    -0.07
    æķ°çIJĨ
    -0.06
     Embedded
    -0.06
    esser
    -0.06
    åĽĽæµ·
    -0.06
     fields
    -0.06
    POSITIVE LOGITS
    大å°ıçļĦ
    0.10
    åħ¨éķ¿
    0.10
     sizes
    0.10
    大å°ı为
    0.09
     Sizes
    0.09
    _sizes
    0.09
    ãĤµãĤ¤ãĤº
    0.09
     fragments
    0.09
     size
    0.09
    frag
    0.09
    Activations Density 0.114%

    No Known Activations