© 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. 9637
    Prev
    Next
    INDEX
    Explanations

    desired url

    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
    æĶ¯æĮģåĬĽåº¦
    -0.11
    åıªä¸º
    -0.10
    æĦıå¢ĥ
    -0.10
    urator
    -0.10
    èĽĭ
    -0.09
    åį´åıĪ
    -0.09
    åĹŁ
    -0.09
    áo
    -0.09
    anship
    -0.09
    è¿Ļ个åIJįåŃĹ
    -0.09
    POSITIVE LOGITS
     desired
    0.19
    ä½łæĥ³
    0.16
     wanted
    0.14
    æĥ³è¦ģ
    0.14
    欲
    0.14
    desired
    0.14
    æīĢéľĢçļĦ
    0.12
     øns
    0.11
    æĦŁåħ´è¶£çļĦ
    0.11
    ä½łè¦ģ
    0.11
    Activations Density 0.348%

    No Known Activations