© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22319
    Prev
    Next
    INDEX
    Explanations

    www

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å®ŀéªĮåŃ¦æł¡
    -0.07
    clos
    -0.06
    è®
    -0.06
    teenth
    -0.06
    伯çī¹
    -0.06
    oldt
    -0.06
    ç¨ĭ
    -0.06
    indr
    -0.06
    ç¾İä¸Ń
    -0.06
    åıij稿
    -0.06
    POSITIVE LOGITS
     she
    0.05
    ogie
    0.05
    大çĻ½
    0.05
     fire
    0.05
     bon
    0.05
     big
    0.05
    lect
    0.05
    ***
    0.04
    ä¼ı
    0.04
    atory
    0.04
    Activations Density 0.002%

    No Known Activations