© 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. 12114
    Prev
    Next
    INDEX
    Explanations

    rugs and carpets

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æ¦ľ
    -0.11
    braco
    -0.10
    æ§IJ
    -0.10
    æĹ©æĻļ
    -0.10
    æĿŀ
    -0.09
    çĪĨçĤ¸
    -0.09
    èµĦ产
    -0.09
    à¹ģà¸Ľà¸¥
    -0.09
    车ä½į
    -0.09
    åĪĽæĸ°èĥ½åĬĽ
    -0.09
    POSITIVE LOGITS
    åľ°æ¯¯
    0.12
     rugs
    0.10
    毯
    0.10
     rug
    0.10
    ì§ľ
    0.09
    ling
    0.09
    踢
    0.09
     Rug
    0.09
     carpets
    0.09
    驼
    0.09
    Activations Density 0.053%

    No Known Activations