© 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. 24015
    Prev
    Next
    INDEX
    Explanations

    is a state

    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
    ç²¾åĵģ
    -0.09
    éļıæīĭ
    -0.08
     naive
    -0.08
    æѤåĪ»
    -0.08
    æ°Ķ
    -0.08
    没人
    -0.08
    è¿Ļä¸ĢåĪ»
    -0.08
     disparate
    -0.08
    代表
    -0.08
     Coh
    -0.08
    POSITIVE LOGITS
    ä¸įåĪĨ
    0.11
    ä¾ĿéĿł
    0.10
    ä¸įçĶ±
    0.09
    åĪĨå¼Ģ
    0.09
    åĪĨå·¥
    0.09
    å®Įåħ¨æĺ¯
    0.09
    çĶ·æĸ¹
    0.09
    åıªè§ģ
    0.09
    ç¦ģæŃ¢
    0.09
    ä¾Ŀèµĸ
    0.09
    Activations Density 0.373%

    No Known Activations