© 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. 9161
    Prev
    Next
    INDEX
    Explanations

    press, media, journalists, interviews

    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
    åĪĽå§ĭ
    -0.09
    æĤ¬
    -0.09
    é¢Ĩ导èĢħ
    -0.09
    æµĴ
    -0.09
    å·
    -0.09
    çŁ³çģ°
    -0.08
    é¦Ĩ
    -0.08
    å·¥ä¸ļåĮĸ
    -0.08
    ç»ĩ
    -0.08
     Degree
    -0.08
    POSITIVE LOGITS
    æİ¥åıĹéĩĩ访
    0.11
    åIJijè®°èĢħ
    0.11
    åıijå¸ĥä¼ļä¸Ĭ
    0.10
    æĸ°éĹ»è®°èĢħ
    0.10
    åıijå¸ĥä¼ļ
    0.10
    æĸ°éĹ»åıijå¸ĥ
    0.10
    éĩĩ访
    0.09
    å¼Ģ设
    0.09
     journalists
    0.09
     press
    0.09
    Activations Density 0.079%

    No Known Activations