© 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. 62874
    Prev
    Next
    INDEX
    Explanations

    friendly against

    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
    UGC
    -0.11
    DCF
    -0.09
    å¤ĸåľ°
    -0.09
    åĴĮ社ä¼ļ
    -0.09
    å¸ĤåĮº
    -0.08
    çİ°éĩijæµģ
    -0.08
    主åŁİåĮº
    -0.08
    éī´åĪ«
    -0.08
    æĦīå¿«
    -0.08
    åħ¥é©»
    -0.08
    POSITIVE LOGITS
    å¼ºåĽ½
    0.15
    æĬ¤çħ§
    0.14
    æľ¬åĽ½
    0.13
    åħ¶ä»ĸåĽ½å®¶
    0.13
    åĩºåħ¥å¢ĥ
    0.13
    å¤§åĽ½
    0.13
    对ä¸ŃåĽ½
    0.13
    åĽŀåĽ½
    0.12
    åIJĦåĽ½
    0.11
    ä¸¤åĽ½
    0.11
    Activations Density 0.184%

    No Known Activations