© 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. 31589
    Prev
    Next
    INDEX
    Explanations

    sponsor, sponsorship, and partner relationships

    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
    è¾į
    -0.10
    çĽ¸äº²
    -0.10
    å¹²éĥ¨éĺŁä¼į
    -0.10
    éļıæŶéļıåľ°
    -0.09
    resa
    -0.09
    iPhone
    -0.09
    ä¸ŃåİŁ
    -0.09
    åľī
    -0.09
    ä»£è¡¨åĽ¢
    -0.08
    æľ¬é¢Ĩ
    -0.08
    POSITIVE LOGITS
    èµŀåĬ©
    0.16
    åįıåĬŀ
    0.13
    åIJĪä½ľä¼Ļä¼´
    0.12
     sponsor
    0.11
    æīĺ管
    0.11
    çļĦ好
    0.11
    èİ·
    0.10
     sponsorship
    0.10
     sponsors
    0.10
    _partner
    0.10
    Activations Density 0.082%

    No Known Activations