© 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. 29596
    Prev
    Next
    INDEX
    Explanations

    specific labels or identifiers

    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
    IFA
    -0.09
    çĦī
    -0.09
     Democr
    -0.09
    èİł
    -0.08
    æĮ¯
    -0.08
    åIJĪä¸Ģ
    -0.08
     Stall
    -0.08
    .imp
    -0.08
    é£İæļ´
    -0.08
     trailer
    -0.08
    POSITIVE LOGITS
    èĥŃ
    0.10
    æĿĥåĪ©
    0.10
    å¿¿
    0.09
    éģį
    0.09
    ä¸įåħ¬å¹³
    0.09
    akis
    0.08
    _KEYBOARD
    0.08
    èį¼
    0.08
    å¦Ĥæŀľæľī
    0.08
     ÙĪاÙĦا
    0.08
    Activations Density 0.103%

    No Known Activations