© 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. 598
    Prev
    Next
    INDEX
    Explanations

    therapeutic context and outcomes

    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
    éĹ¼
    -0.09
    æŃ¥æŃ¥
    -0.08
    好ä¸į好
    -0.08
    æ¸į
    -0.08
    å´ĩå°ļ
    -0.08
     Jub
    -0.07
    è·ŁæĪij
    -0.07
    vars
    -0.07
     DK
    -0.07
    éĺ
    -0.07
    POSITIVE LOGITS
    anden
    0.10
    radient
    0.10
    çĬį
    0.10
    MSC
    0.10
    VES
    0.09
    .EntityManager
    0.09
    èµİ
    0.09
    åľ°æ®µ
    0.09
    éľ°
    0.09
    æģIJ
    0.09
    Activations Density 0.088%

    No Known Activations