© 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. 10087
    Prev
    Next
    INDEX
    Explanations

    historic or special designation

    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
    å¤ĸåĮħ
    -0.11
    å¹³åĩ¡
    -0.09
    æľĭåıĭ们对
    -0.08
    æĪª
    -0.08
    å¾Ĥ
    -0.08
    æĿŁ
    -0.08
    èĥĦ
    -0.08
    åį«çĶŁ
    -0.08
    èĶij
    -0.08
    æĭ¥æĬ¤
    -0.08
    POSITIVE LOGITS
    å½ĵä¹ĭæĹłæĦ§
    0.10
    åĽłä¸ºå®ĥ
    0.10
    ä¸Ģ级
    0.10
    éĻ©
    0.09
    åİŁåĽłä¹ĭä¸Ģ
    0.09
     Parade
    0.09
    ä¸Ģç±»
    0.09
    åIJįåįķ
    0.09
    æīĢä»¥åľ¨
    0.09
    天河
    0.09
    Activations Density 0.177%

    No Known Activations