© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22613
    Prev
    Next
    INDEX
    Explanations

    usage of or before

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĿ¥çļĦ
    -0.10
    º
    -0.10
    ito
    -0.09
    ãĤīãĤĮãģŁ
    -0.09
    .Lib
    -0.09
    pora
    -0.09
    velt
    -0.09
    bis
    -0.09
    çĸ«æĥħå½±åĵį
    -0.08
    æľĪä¸ĭ
    -0.08
    POSITIVE LOGITS
    0.10
    éĩı
    0.10
    大åħ¨
    0.09
    ult
    0.09
    rough
    0.09
    ëģĶ
    0.09
     gim
    0.09
     ÑħоÑĤ
    0.08
    raquo
    0.08
    åħħæ²Ľ
    0.08
    Activations Density 0.024%

    No Known Activations