© 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. 22475
    Prev
    Next
    INDEX
    Explanations

    a noun follows

    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
    ansa
    -0.07
    ums
    -0.06
    å½ĵå½ĵ
    -0.06
    tics
    -0.06
    ä¸įçĿĢ
    -0.06
    acto
    -0.06
    ehm
    -0.06
    å¾Īå¿«çļĦ
    -0.06
    ahan
    -0.06
    indsight
    -0.06
    POSITIVE LOGITS
    éĺ¶çº§
    0.06
    åľ¨å¤©
    0.05
     photograph
    0.05
    sh
    0.05
    ium
    0.05
    elj
    0.05
    并éĩį
    0.05
    éĺ¶çº§çļĦ
    0.05
     Gla
    0.05
    çĽ
    0.05
    Activations Density 0.011%

    No Known Activations