© 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. 10977
    Prev
    Next
    INDEX
    Explanations

    organizations and standards bodies

    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
    ires
    -0.09
    unan
    -0.09
    é£İæīĩ
    -0.08
    HAND
    -0.08
     Rath
    -0.08
    assen
    -0.08
    åºĦ
    -0.08
    çѦ
    -0.08
    å¹³çŃī
    -0.08
    kea
    -0.08
    POSITIVE LOGITS
    è¹Ĭ
    0.09
    é¦Ĭ
    0.09
    访
    0.09
    å¿ĥæĢĿ
    0.09
    è¿Ļæĺ¯æĪij
    0.09
    éĥ¨éķ¿
    0.09
    ItemType
    0.08
    å°±æĺ¯ä¸ºäºĨ
    0.08
    治好
    0.08
    ู
    0.08
    Activations Density 0.038%

    No Known Activations