© 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. 58627
    Prev
    Next
    INDEX
    Explanations

    accessing and sharing information

    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
    éĢĤ
    -0.09
    åŃļ
    -0.09
    å°½åĬĽ
    -0.08
     nặng
    -0.08
    æĺ¯ä¸ºäºĨ
    -0.08
    è¿ĺæĺ¯æ¯Ķè¾ĥ
    -0.08
    èĥ
    -0.08
    çī¹åĪ«æĺ¯åľ¨
    -0.08
    ä¹Łæľīä¸ĢäºĽ
    -0.08
    åĽŀäºĭ
    -0.08
    POSITIVE LOGITS
    å¾Īæĸ¹ä¾¿
    0.13
    åīįæīĢæľª
    0.11
     niche
    0.10
    çŀ¬éĹ´
    0.10
    éļıæŶéļıåľ°
    0.10
    åīįæīĢæľªæľī
    0.10
    éļıæŶ
    0.09
    çŀ¬
    0.09
    空åīį
    0.09
     unprecedented
    0.09
    Activations Density 0.142%

    No Known Activations