© 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. 22353
    Prev
    Next
    INDEX
    Explanations

    football positions

    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
    olph
    -0.06
    amet
    -0.06
    ÑģÑĤано
    -0.06
    ainless
    -0.06
    emade
    -0.05
    raca
    -0.05
    lescope
    -0.05
    mium
    -0.05
    atik
    -0.05
    à¸ķัวà¸Ĥà¸Ńà¸ĩ
    -0.05
    POSITIVE LOGITS
     Needed
    0.05
     anything
    0.05
     needed
    0.05
    wing
    0.05
    ãĥĺãĥ«
    0.05
    åĸĦ
    0.05
    é¤
    0.05
     higien
    0.05
    ä»»
    0.05
    让æĤ¨
    0.05
    Activations Density 0.064%

    No Known Activations