© 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. 12251
    Prev
    Next
    INDEX
    Explanations

    flows and enhancement

    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
    éĻ·
    -0.09
    iec
    -0.09
    vest
    -0.08
    åĥ»
    -0.08
    æ§Į
    -0.08
    comed
    -0.08
    rouch
    -0.08
    举éĥ¨
    -0.08
     pred
    -0.08
    fers
    -0.08
    POSITIVE LOGITS
    èĤ´
    0.10
    çĤ¹å¤´
    0.09
    eful
    0.09
    å¼łå®¶
    0.09
    papers
    0.09
    åĩıè½»
    0.09
    iph
    0.08
    è¿Ŀ
    0.08
    bage
    0.08
    礼è²Į
    0.08
    Activations Density 0.164%

    No Known Activations