© 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. 33640
    Prev
    Next
    INDEX
    Explanations

    t followed by common word endings

    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
    åIJģ
    -0.11
    ä¸įå°ij人
    -0.09
    大éĥ¨åĪĨ人
    -0.09
    orce
    -0.09
    imming
    -0.09
    ingly
    -0.09
    å°±æĺ¯è¦ģ
    -0.08
    ä¸ĢåĪ»
    -0.08
    못
    -0.08
    è®®åijĺ
    -0.08
    POSITIVE LOGITS
    çĬģ
    0.09
    æł¼å°Ķ
    0.09
    loo
    0.09
    crow
    0.09
    èĥ½æ»¡è¶³
    0.08
    çİ¥
    0.08
    оÑĨен
    0.08
    woods
    0.08
    å¯Ĩå°ģ
    0.08
    æľīä¸ĢçĤ¹
    0.08
    Activations Density 0.024%

    No Known Activations