© 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. 22460
    Prev
    Next
    INDEX
    Explanations

    me dating

    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
    джи
    -0.08
    gade
    -0.08
    ÑĢÑĥм
    -0.07
    alse
    -0.07
    дÑĸй
    -0.07
    минÑĥ
    -0.07
    話é¡Į
    -0.07
     suites
    -0.07
    psy
    -0.07
    åѤå¯Ĥ
    -0.07
    POSITIVE LOGITS
    “
    0.05
    gether
    0.05
     “
    0.05
    "
    0.05
    /
    0.05
    r
    0.05
    0.05
    '
    0.05
    .r
    0.05
     r
    0.04
    Activations Density 0.001%

    No Known Activations