© 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. 16862
    Prev
    Next
    INDEX
    Explanations

    parenthetical citations

    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
    elaar
    -0.06
    apest
    -0.06
    Amb
    -0.06
    uly
    -0.06
    æ¡ģ
    -0.06
    aran
    -0.06
    rng
    -0.06
    ocom
    -0.06
    ·
    -0.06
    .DialogInterface
    -0.06
    POSITIVE LOGITS
     jeden
    0.05
    axe
    0.05
     Mime
    0.05
    à§ĩà¦ķ
    0.05
     mechanisms
    0.04
    ippers
    0.04
     designing
    0.04
    Clause
    0.04
    ä¸įæĮ¯
    0.04
    éĿłåīį
    0.04
    Activations Density 0.017%

    No Known Activations