© 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. 30427
    Prev
    Next
    INDEX
    Explanations

    film titles or names

    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
    _FMT
    -0.11
    okedex
    -0.10
    åıĪä¸Ģ次
    -0.09
    æĹ©æĻļ
    -0.09
     Fry
    -0.09
    ued
    -0.09
    WithError
    -0.09
    ầm
    -0.09
    壳
    -0.09
    okus
    -0.09
    POSITIVE LOGITS
    etty
    0.11
    离ä¸įå¼Ģ
    0.09
    è·Ľ
    0.09
    ean
    0.09
     nonsense
    0.09
     exc
    0.08
    ä¸įå¾Ĺä¸į说
    0.08
    grim
    0.08
    人身
    0.08
     Newsletter
    0.08
    Activations Density 0.001%

    No Known Activations