© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40425
    Prev
    Next
    INDEX
    Explanations

    travel packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    fulness
    -0.11
    iscal
    -0.10
    ium
    -0.10
    ship
    -0.10
    urer
    -0.09
    PageIndex
    -0.08
    ships
    -0.08
    ubar
    -0.08
    lessly
    -0.08
    ral
    -0.08
    POSITIVE LOGITS
    :flutter
    0.09
    çĿ¦
    0.09
    é²²
    0.09
    æ½¢
    0.09
    ¡
    0.09
    olini
    0.09
    AGING
    0.09
    _AST
    0.09
     оÑĢи
    0.09
    éģ
    0.09
    Activations Density 0.027%

    No Known Activations