© 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. 16612
    Prev
    Next
    INDEX
    Explanations

    same

    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
    .va
    -0.09
    ÑħваÑĤ
    -0.09
    å°±æĺ¯è¦ģ
    -0.09
    TIMER
    -0.08
    borough
    -0.08
    illaume
    -0.08
    orsi
    -0.08
    _IOS
    -0.08
    ellite
    -0.08
    ä¸įåĨįæĺ¯
    -0.08
    POSITIVE LOGITS
    -sex
    0.10
    ast
    0.09
    æ°´åĩĨ
    0.09
    yun
    0.09
     same
    0.08
    åħ¶ä»ĸåĽ½å®¶
    0.08
    odge
    0.08
    å½ĵåĪĿ
    0.08
    ç¿
    0.08
    æijĩ
    0.08
    Activations Density 0.133%

    No Known Activations