© 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. 6629
    Prev
    Next
    INDEX
    Explanations

    people and phrases

    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
    èħ¿éĥ¨
    -0.09
    ä¸įåĪĨ
    -0.08
     RSVP
    -0.08
    ä¸Ĭ级
    -0.08
    net
    -0.08
    á»·
    -0.08
     perk
    -0.08
    éĽĨåĽ¢
    -0.08
    äºĨä¸įå°ij
    -0.08
    丰
    -0.07
    POSITIVE LOGITS
    éĤ£äºĽ
    0.18
     những
    0.11
    ä¼Ĺå¤ļ
    0.11
     those
    0.11
    æĹłæķ°
    0.11
    éĤ£åıª
    0.10
    æĹłè¾ľ
    0.10
    ÑģÑĤÑĢа
    0.10
    ãģĤãģ®
    0.10
    éĤ£ä¹Īå¤ļ
    0.10
    Activations Density 0.038%

    No Known Activations