© 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. 22365
    Prev
    Next
    INDEX
    Explanations

    solve or find mathematical problems

    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
    缸çīĩ
    -0.06
     Nh
    -0.06
    marsh
    -0.06
    åĨħéļľ
    -0.06
    heimer
    -0.06
    udah
    -0.06
    表çİ°åĩºæĿ¥çļĦ
    -0.06
    allax
    -0.06
    -abortion
    -0.06
    /Internal
    -0.05
    POSITIVE LOGITS
    ests
    0.06
    Âł
    0.06
    g
    0.06
    ys
    0.06
     real
    0.06
    à¹Į
    0.05
    urnal
    0.05
    esi
    0.05
    edd
    0.05
    yz
    0.05
    Activations Density 0.004%

    No Known Activations