© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39218
    Prev
    Next
    INDEX
    Explanations

    vasopressin and peptides

    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
    åIJĽåŃIJ
    -0.11
    æĪķ
    -0.10
    è½®
    -0.10
    罩
    -0.10
    è¾Ĺ
    -0.09
    ë¶ĵ
    -0.09
    ecz
    -0.09
    edo
    -0.09
    ä¸įå®Į
    -0.09
    isel
    -0.09
    POSITIVE LOGITS
     peptide
    0.09
     peptides
    0.09
     vein
    0.08
    æľ«ç«¯
    0.08
    æľ«
    0.08
    èĽĽ
    0.08
     Zip
    0.08
    å²Ķ
    0.08
     compr
    0.08
    Zip
    0.08
    Activations Density 0.894%

    No Known Activations