© 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. 29716
    Prev
    Next
    INDEX
    Explanations

    costs and consequences

    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
    amd
    -0.09
    MIT
    -0.09
    iper
    -0.09
    æĮ½åĽŀ
    -0.09
    æºIJæºIJ
    -0.09
    èĮĹ
    -0.09
    çĥŃéĩı
    -0.09
    ACL
    -0.08
     spilled
    -0.08
    ç²¾ç¥ŀæĸĩæĺİ
    -0.08
    POSITIVE LOGITS
    å±ĬæŶ
    0.12
    å®ŀæĸ½
    0.11
    æĸ½è¡Į
    0.10
    åıĹåĪ°å½±åĵį
    0.10
    åıĹå½±åĵį
    0.10
     implementation
    0.10
    Affected
    0.10
    åıįåĵį
    0.10
    å®ŀæĸ½æĸ¹æ¡Ī
    0.10
    ä»Ĭãģ¾ãģ§
    0.09
    Activations Density 0.135%

    No Known Activations