© 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. 16714
    Prev
    Next
    INDEX
    Explanations

    official documents and records

    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
    istically
    -0.08
    lott
    -0.06
    legg
    -0.06
    ä¸įçķĻ
    -0.06
    ombra
    -0.06
    ETTE
    -0.06
    lard
    -0.06
    алÑĮÑı
    -0.06
    çªį
    -0.06
    æľīåı²
    -0.06
    POSITIVE LOGITS
    è°ĥ
    0.06
    çĶĺ
    0.05
    creenshot
    0.05
     tune
    0.05
    uned
    0.05
    Distribution
    0.05
     screenshot
    0.05
    ìŀĦìĿĦ
    0.05
     tuning
    0.05
     tuned
    0.05
    Activations Density 0.019%

    No Known Activations