© 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. 50530
    Prev
    Next
    INDEX
    Explanations

    percent of

    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
    æľīä¸Ģä½į
    -0.12
    太太
    -0.09
    ä¸Ģ群人
    -0.09
    ä¸Ģ个人
    -0.09
    驹
    -0.09
    游åĩ»éĺŁ
    -0.08
    åĩłåIJį
    -0.08
    ä¸ĢæĿ¯
    -0.08
     Patron
    -0.08
    åIJ¬åIJ¬
    -0.08
    POSITIVE LOGITS
    æĥħåĨµä¸ĭ
    0.11
    漩
    0.10
    åıĹ访
    0.10
    表示
    0.09
    erton
    0.09
    çĤ¼
    0.09
    æĿ¡ä»¶ä¸ĭ
    0.08
    è·ĭ
    0.08
    çľĭå®Į
    0.08
     полÑĮзоваÑĤ
    0.08
    Activations Density 0.050%

    No Known Activations