© 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. 49616
    Prev
    Next
    INDEX
    Explanations

    Copyright

    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
    assy
    -0.10
    è¿ĺä¸įå¤Ł
    -0.09
    itet
    -0.09
    æīĢéľĢè¦ģçļĦ
    -0.09
    ä¸įåĩºæĿ¥
    -0.09
    èĥ½å¤Łåľ¨
    -0.09
    baugh
    -0.09
    rome
    -0.08
    讪
    -0.08
    饱满
    -0.08
    POSITIVE LOGITS
    乡éķĩ
    0.11
    çĽĬ
    0.09
    榴
    0.09
     concess
    0.08
    endar
    0.08
    å½Ĵ
    0.08
    å£
    0.08
     ÑĤомÑĥ
    0.08
    arti
    0.08
     Lil
    0.08
    Activations Density 0.002%

    No Known Activations