© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9543
    Prev
    Next
    INDEX
    Explanations

    what makes you ask

    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
     поÑĤом
    -0.09
    åĿļä¿¡
    -0.09
    绯
    -0.08
    欲
    -0.08
    ä¸ĵéŨ
    -0.08
     cogn
    -0.08
    íķĺëĬĶëį°
    -0.08
    aldi
    -0.08
    éĢıæĺİ
    -0.08
    åĬª
    -0.08
    POSITIVE LOGITS
    人çī©
    0.10
    ä¸Ģç¬Ķ
    0.09
    !--
    0.09
    ymm
    0.09
     Trash
    0.09
    æ»Ĥ
    0.09
    å½ĵçĦ¶æĺ¯
    0.09
    åıĸæ¶Ī
    0.09
    å§ĵåIJį
    0.09
    èĢģ人家
    0.08
    Activations Density 0.040%

    No Known Activations