© 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. 8950
    Prev
    Next
    INDEX
    Explanations

    in this regard / in this sense

    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
    åij
    -0.10
    .addValue
    -0.10
    à¹ģห
    -0.09
     Heller
    -0.09
    udi
    -0.09
    دار
    -0.09
    åĩĢæ°´
    -0.09
    èĿł
    -0.09
    é«ĺæ½®
    -0.08
    asar
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸ĢçĤ¹
    0.19
    è¿ĻçĤ¹
    0.17
    è¿Ļæĸ¹éĿ¢
    0.17
    æĸ¹éĿ¢
    0.13
    æĸ¹éĿ¢çļĦ
    0.11
     aspect
    0.11
    è¿Ļ个éĹ®é¢ĺ
    0.11
     aspects
    0.11
    è¿ĺæĺ¯æ¯Ķè¾ĥ
    0.10
    åľ¨è¿Ļæĸ¹éĿ¢
    0.10
    Activations Density 0.033%

    No Known Activations