© 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. 12442
    Prev
    Next
    INDEX
    Explanations

    exclude or include

    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
    æ»ij
    -0.09
    ç¿ħ
    -0.09
    omin
    -0.09
    åĩ¤
    -0.09
    ools
    -0.09
    åĮ¯
    -0.09
    åĻ
    -0.08
    PPER
    -0.08
    ouro
    -0.08
    æľĭ
    -0.08
    POSITIVE LOGITS
    涵çĽĸ
    0.14
    éĤ£äºĽ
    0.13
    è¦ĨçĽĸ
    0.13
    涵çĽĸäºĨ
    0.12
    è¿ĺåĮħæĭ¬
    0.11
     encompass
    0.11
    å¤Ń
    0.10
    covers
    0.10
     Covers
    0.10
    è¦ĨçĽĸçİĩ
    0.10
    Activations Density 0.197%

    No Known Activations