© 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. 24217
    Prev
    Next
    INDEX
    Explanations

    La Crosse, Lee, Anyang, Heidelberg, Cruz, Dayton

    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
    å°Ĭéĩį
    -0.12
    æłİ
    -0.09
    hip
    -0.08
    ighth
    -0.08
    4
    -0.08
    0
    -0.08
    æ¨Ł
    -0.08
    5
    -0.08
     Jab
    -0.08
     respect
    -0.08
    POSITIVE LOGITS
    ensis
    0.12
    -area
    0.10
    åľ°åĮºçļĦ
    0.10
     Ãľniversitesi
    0.10
    ä¸ĢéĹ´
    0.10
    shire
    0.09
    tesy
    0.09
    หาย
    0.09
    çĹķ
    0.09
    åºĬ
    0.09
    Activations Density 0.275%

    No Known Activations