© 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. 26395
    Prev
    Next
    INDEX
    Explanations

    tools and craft items

    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
    ä¾ĽçĶµ
    -0.09
    åŀĽ
    -0.09
    棵
    -0.08
    çĶŁéķ¿
    -0.08
    ä¸įå¤ļ
    -0.08
    åĴİ
    -0.08
    bildung
    -0.08
    å¢ŀéķ¿
    -0.08
    INTR
    -0.08
    NG
    -0.08
    POSITIVE LOGITS
    åŃĶéĽĢ
    0.09
     (~(
    0.09
    èĬ¬
    0.08
    éļıä¹ĭ
    0.08
    è¾Ľåĭ¤
    0.08
    uem
    0.08
    dag
    0.08
    èĢĴ
    0.08
     bookmark
    0.08
    riel
    0.08
    Activations Density 0.203%

    No Known Activations