© 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. 22478
    Prev
    Next
    INDEX
    Explanations

    spinach leaves

    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
    eni
    -0.05
    isson
    -0.05
    interval
    -0.05
     jab
    -0.05
    peri
    -0.05
    endis
    -0.05
     interval
    -0.05
    лак
    -0.05
    jung
    -0.05
    imiters
    -0.05
    POSITIVE LOGITS
    污
    0.07
    ÑĥÑģÑĤа
    0.06
    ardu
    0.06
    ware
    0.06
    loat
    0.06
    heet
    0.06
    ç®Ķ
    0.06
     ÑĢазогÑĢе
    0.06
    ãģĺãĤģ
    0.06
    第äºĮ款
    0.06
    Activations Density 0.003%

    No Known Activations