© 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. 22550
    Prev
    Next
    INDEX
    Explanations

    whereas / enquanto

    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
    ãģĦãĤĭ
    -0.08
    niÄį
    -0.07
    cest
    -0.07
    oved
    -0.07
    ergeb
    -0.07
    ÙĦÙĦ
    -0.07
    schluss
    -0.06
    brero
    -0.06
    voli
    -0.06
    scriber
    -0.06
    POSITIVE LOGITS
    /or
    0.06
    age
    0.06
    ä½Ĩä¸įéĻIJäºİ
    0.06
    ation
    0.06
    ings
    0.06
    esa
    0.06
     Se
    0.06
    ness
    0.06
    Ú¯ÛĮ
    0.05
    èĬ±éĥ½
    0.05
    Activations Density 0.006%

    No Known Activations