© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51486
    Prev
    Next
    INDEX
    Explanations

    such as those

    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
    alem
    -0.10
    ulp
    -0.09
    è¿ĻäºĽä¸ľè¥¿
    -0.09
    ä¸įç¡®å®ļ
    -0.09
    éĥ½æĥ³
    -0.09
    åŀ®
    -0.09
    ocale
    -0.09
    åĽ¤
    -0.09
    astos
    -0.08
    æĬµ
    -0.08
    POSITIVE LOGITS
    便
    0.09
    å¢Ł
    0.08
    çļĦæīĭ
    0.08
    inky
    0.08
    çļĦåĬ¨åĬĽ
    0.08
    çĶļèĩ³æĺ¯
    0.08
    å¸ĤåĮº
    0.08
    ä½ľèĢħæľ¬äºº
    0.08
     mer
    0.08
    æŃ»èĢħ
    0.08
    Activations Density 0.162%

    No Known Activations