© 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. 59111
    Prev
    Next
    INDEX
    Explanations

    issues in discussions

    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
    ç°Į
    -0.10
    丰æĶ¶
    -0.09
    æĮ½
    -0.08
     Xiaomi
    -0.08
     rot
    -0.08
    éĴ°
    -0.08
    ee
    -0.08
    å°ıç±³
    -0.08
     External
    -0.08
    大æĪ·
    -0.08
    POSITIVE LOGITS
    æ¡£
    0.09
    åĴĮåıijå±ķ
    0.09
    è¿«
    0.09
    dependence
    0.09
    æ¤ĵ
    0.09
    æĢħ
    0.09
    æĦıè¯Ĩ
    0.08
    rink
    0.08
    æķ´ä¸ªäºº
    0.08
     aides
    0.08
    Activations Density 0.028%

    No Known Activations