© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19445
    Prev
    Next
    INDEX
    Explanations

    pyd.io SDK Labs Kirby core

    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
     Loren
    -0.09
     coupons
    -0.08
    è¯Ŀ说
    -0.08
    åĬŀ
    -0.08
    è§Ħç¨ĭ
    -0.08
    æĴij
    -0.08
    udent
    -0.08
    IPv
    -0.07
    çŁĽçĽ¾
    -0.07
     cows
    -0.07
    POSITIVE LOGITS
    人家
    0.10
    ervers
    0.10
    注æĦıåĬĽ
    0.09
    ulet
    0.09
    åħļåĴĮæĶ¿åºľ
    0.09
    æĺ¥ç§ĭ
    0.09
    deo
    0.09
    æijĩ头
    0.08
    gar
    0.08
    VE
    0.08
    Activations Density 0.274%

    No Known Activations