© 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. 3591
    Prev
    Next
    INDEX
    Explanations

    strive for or to

    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
    éĢ¡
    -0.10
    注éĩį
    -0.10
    едÑĮ
    -0.10
    orrent
    -0.09
    迤
    -0.09
    è§ģè¿ĩ
    -0.09
    endum
    -0.09
    æ±²
    -0.09
    eme
    -0.09
    éĩįè§Ĩ
    -0.09
    POSITIVE LOGITS
    é«ĺçļĦ
    0.10
    æĽ´é«ĺçļĦ
    0.10
    åģļåĪ°
    0.10
    æľīä¸Ģ天
    0.08
    æĪIJ为
    0.08
    CALE
    0.08
    åģļ个
    0.08
    天空
    0.08
    è¶Ĭé«ĺ
    0.08
    æĹ¥äº§
    0.08
    Activations Density 0.025%

    No Known Activations