© 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. 47943
    Prev
    Next
    INDEX
    Explanations

    Etsy, Roku, ietf, ETS, Shopify

    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
    bs
    -0.08
    ÅĽ
    -0.08
    abad
    -0.08
    æľīåĬ©
    -0.08
    izi
    -0.08
    å¼Ĥ
    -0.08
    odom
    -0.07
    çĽ¼æľĽ
    -0.07
    quier
    -0.07
    ine
    -0.07
    POSITIVE LOGITS
    moid
    0.10
    ÙĥÙĬ
    0.10
    ÙĨد
    0.10
    人åĬĽ
    0.09
    å§Ķä¼ļ
    0.09
     forth
    0.09
    çķĮçļĦ
    0.09
    æĤłæĤł
    0.09
    饯
    0.09
    ymbol
    0.09
    Activations Density 0.001%

    No Known Activations