© 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. 3033
    Prev
    Next
    INDEX
    Explanations

    a couple of

    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
    çļĦä¸Ģéĥ¨åĪĨ
    -0.09
    åŀĭä¼ģä¸ļ
    -0.09
    å¤ļæķ°
    -0.09
     various
    -0.08
    ä¸ĢéŨ
    -0.08
    aud
    -0.08
     Various
    -0.08
    å¤ļå±Ĥ次
    -0.08
    ä¸Ģ个人
    -0.08
    ä¹ĭå¤Ħ
    -0.08
    POSITIVE LOGITS
     dozen
    0.17
    ä¸įéĶĻçļĦ
    0.11
     hundred
    0.10
    æĸ¹éĿ¢
    0.10
    endon
    0.10
    å±ĤéĿ¢
    0.10
    å¾Īéĩįè¦ģçļĦ
    0.10
    æĪĸå¤ļ
    0.09
    åį®
    0.09
    ghan
    0.09
    Activations Density 0.008%

    No Known Activations