© 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. 7205
    Prev
    Next
    INDEX
    Explanations

    start by saying

    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
    abay
    -0.09
    ua
    -0.09
    ä¸Ģæĺ¯
    -0.08
    å°¤åħ¶
    -0.08
    éĻ¤æѤ
    -0.08
    ä¸ĢéĿ¢
    -0.08
    eton
    -0.08
    igne
    -0.08
    orate
    -0.08
    etty
    -0.08
    POSITIVE LOGITS
    æĪijä»¬çŁ¥éģĵ
    0.10
    ãģĿãĤĤãģĿãĤĤ
    0.10
    éĥ½çŁ¥éģĵ
    0.10
    æĪijä¸įæĺ¯
    0.10
    èķĪ
    0.10
     Ital
    0.10
    姥
    0.09
    itals
    0.09
    è¿Ļ个åIJįåŃĹ
    0.09
    ä¸įè¦ģ太
    0.09
    Activations Density 0.103%

    No Known Activations