© 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. 59090
    Prev
    Next
    INDEX
    Explanations

    qualifications and attributes

    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
    ç³»åĪĹ产åĵģ
    -0.10
    纾
    -0.10
    æĽĻ
    -0.10
    è¿Ļä¸Ģ次
    -0.10
    ä¸įå¿į
    -0.10
     Classified
    -0.10
    åīįæīĢæľªæľī
    -0.09
    èµŃ
    -0.09
    ä¸įèĪį
    -0.09
    å½ĵä½ľ
    -0.09
    POSITIVE LOGITS
    çľĭéĩį
    0.12
    èĢĥéĩı
    0.10
    åĽłç´ł
    0.10
    è¡¡éĩı
    0.10
    èĦ±ç¦»
    0.10
    èŤ
    0.10
     criteria
    0.10
    è¦ģæľī
    0.10
    æ±°
    0.10
    åħ·å¤ĩ
    0.10
    Activations Density 0.091%

    No Known Activations