© 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. 59131
    Prev
    Next
    INDEX
    Explanations

    except phrase construction

    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
     zwar
    -0.10
    æľīæĿ¡ä»¶çļĦ
    -0.10
    çĻ¾ç§ij
    -0.09
    æľīå¿ħè¦ģ
    -0.09
    ãģķãģĦ
    -0.09
    ä¹Łè®¸æĺ¯
    -0.09
    çĿ¨
    -0.08
    æķĽ
    -0.08
    éĤ£ç§į
    -0.08
    çĶļèĩ³æĺ¯
    -0.08
    POSITIVE LOGITS
    ани
    0.08
     декабÑĢÑı
    0.08
    åIJİèĢħ
    0.08
    usher
    0.08
    çİ°å®ŀä¸Ń
    0.08
    åıijå¸ĥæŶéĹ´
    0.08
     Milit
    0.08
    .ser
    0.08
    æĭ£
    0.07
     Alexander
    0.07
    Activations Density 0.034%

    No Known Activations