© 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. 22449
    Prev
    Next
    INDEX
    Explanations

    struggles from or with

    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
    Negative Logits
    é¢Ŀ为
    -0.06
    å®ŀ
    -0.05
     Grad
    -0.05
    ud
    -0.05
    æĽ´æľīåĪ©äºİ
    -0.05
    otrop
    -0.05
    гаÑĢ
    -0.05
    ci
    -0.05
    cents
    -0.05
    owing
    -0.05
    POSITIVE LOGITS
    apper
    0.06
    unken
    0.06
    éĿŀ常é«ĺçļĦ
    0.06
    бол
    0.06
    à¹Ģม
    0.06
    vester
    0.06
    icus
    0.06
     übermittelt
    0.06
    antum
    0.06
    aket
    0.06
    Activations Density 0.010%

    No Known Activations