© 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. 60729
    Prev
    Next
    INDEX
    Explanations

    MTV series

    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
    éĩįä¸Ń
    -0.11
    à¸Īำหà¸Ļ
    -0.10
    -body
    -0.10
    iman
    -0.10
    æģ½
    -0.09
    беж
    -0.09
    è·¡
    -0.09
    被æī§è¡Į
    -0.09
    å°Ĭæķ¬
    -0.09
    该éĻ¢
    -0.09
    POSITIVE LOGITS
    åı²ä¸Ĭ
    0.11
    åĨĮ
    0.09
     Vulcan
    0.08
    åĪ«è¯´
    0.08
    å·¥ä½ľèĢħ
    0.08
    çĪ½
    0.08
    rections
    0.08
    çĶŁæ¶¯
    0.08
    èĪ«
    0.08
    åı²ä¸ĬæľĢ
    0.08
    Activations Density 0.006%

    No Known Activations