© 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. 30749
    Prev
    Next
    INDEX
    Explanations

    because

    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
    éļĶ
    -0.09
     ya
    -0.08
    æľĪä¸Ń
    -0.08
    æĬĬæı¡
    -0.08
    ci
    -0.08
    ä¿¡ä»»
    -0.08
    å¾Ĺä½ı
    -0.08
    大çģ«
    -0.08
    Either
    -0.08
    lich
    -0.08
    POSITIVE LOGITS
    æĺ¯åĽłä¸º
    0.35
    æĺ¯ä¸ºäºĨ
    0.27
    ä¹ĭæīĢ以
    0.24
    è¿Ļæĺ¯åĽłä¸º
    0.23
    çļĦåİŁåĽł
    0.23
    å°±æĺ¯åĽłä¸º
    0.20
    åĽłä¸º
    0.20
    åıªæĺ¯ä¸ºäºĨ
    0.20
    åĽłä¸ºå®ĥ
    0.20
    å°±æĺ¯ä¸ºäºĨ
    0.19
    Activations Density 0.243%

    No Known Activations