© 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. 3023
    Prev
    Next
    INDEX
    Explanations

    url or hurl

    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
    yan
    -0.10
    ç¥ĵ
    -0.10
    çĪ¿
    -0.10
     getItemCount
    -0.09
    .onNext
    -0.09
    owe
    -0.09
    åħ¶ä»ĸçļĦ
    -0.09
    çı©
    -0.09
    ä¸įçĶ±
    -0.09
    ics
    -0.09
    POSITIVE LOGITS
    iness
    0.12
    ingly
    0.10
    ing
    0.09
    å¿ĥåºķ
    0.09
    åIJĪãģĦ
    0.08
    ings
    0.08
    entina
    0.08
    onom
    0.08
    éļĻ
    0.08
    shaw
    0.08
    Activations Density 0.018%

    No Known Activations