© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59167
    Prev
    Next
    INDEX
    Explanations

    this: media/content descriptors

    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
    Negative Logits
     Jame
    -0.09
     pie
    -0.09
    éĤ£ä¹Īå¤ļ
    -0.09
    /=
    -0.08
    段
    -0.08
    è§
    -0.08
    á»Ķ
    -0.08
    å¦Ĥä½ķåİ»
    -0.08
    çĹħæ¯ĴæĦŁæŁĵ
    -0.08
    oka
    -0.08
    POSITIVE LOGITS
    æķijæµİ
    0.09
    lian
    0.08
    èį·
    0.08
    æ·»
    0.08
    otto
    0.08
    ãĥĹãĥ©ãĤ¹
    0.08
    ä¸ĬæĬ¥
    0.08
    å°Ĩåľ¨
    0.08
    æű
    0.08
    WT
    0.08
    Activations Density 0.041%

    No Known Activations