© 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. 63881
    Prev
    Next
    INDEX
    Explanations

    Jr, III, II, names

    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
    ç¼®
    -0.10
    roach
    -0.09
    好人
    -0.09
    itionally
    -0.08
    åĶ±
    -0.08
    èĥĨ
    -0.08
    illow
    -0.08
    æħ¶
    -0.08
    踵
    -0.08
    åIJ¦
    -0.08
    POSITIVE LOGITS
     Jr
    0.20
     III
    0.16
    ä¸Ģä¸ĸ
    0.15
    III
    0.15
     II
    0.15
    âħ
    0.14
     jr
    0.13
    II
    0.13
    ä¸īæĺ¯
    0.13
    äºĮ代
    0.12
    Activations Density 0.481%

    No Known Activations