© 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. 22348
    Prev
    Next
    INDEX
    Explanations

    the word 'and'

    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
    ive
    -0.05
    ivent
    -0.05
    iveau
    -0.05
    addir
    -0.05
    otti
    -0.05
    ÑĹ
    -0.05
    niest
    -0.05
    mond
    -0.05
    abas
    -0.05
    stens
    -0.05
    POSITIVE LOGITS
    oriously
    0.10
    ãĥ³
    0.09
    zelfde
    0.08
    Ñĭ
    0.07
    ãĤĬ
    0.07
    s
    0.07
    sik
    0.07
    ات
    0.07
    bürger
    0.07
    atively
    0.06
    Activations Density 0.059%

    No Known Activations