© 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. 62894
    Prev
    Next
    INDEX
    Explanations

    disappointing results and performance

    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
    åIJĦæł·
    -0.11
    æľīæķĪæĢ§
    -0.11
    ic
    -0.09
    è¥ģ
    -0.09
    eker
    -0.09
    ä¸įæĺĵ
    -0.09
    骡
    -0.09
    ä¸ĩäºĭ
    -0.08
    èĤĩäºĭ
    -0.08
    ä¸įè¦ģ太
    -0.08
    POSITIVE LOGITS
    ingly
    0.13
    ably
    0.10
    ively
    0.09
    æĥĬ
    0.09
    .har
    0.09
     Barn
    0.08
    ença
    0.08
    身å¿ĥ
    0.08
    ower
    0.08
    owitz
    0.08
    Activations Density 0.003%

    No Known Activations