© 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. 4995
    Prev
    Next
    INDEX
    Explanations

    spectroscopic analysis and identification

    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
    æ±ĩ
    -0.11
    canonical
    -0.09
    éĻ¢éķ¿
    -0.08
    åĮ¯
    -0.08
    kap
    -0.08
    æľĢå¤ļ
    -0.08
    èµĦæľ¬ä¸»ä¹ī
    -0.08
    (ld
    -0.08
    说çļĦè¯Ŀ
    -0.08
    æ´½
    -0.08
    POSITIVE LOGITS
    è¿Ļå¼ł
    0.09
    stre
    0.09
     Vit
    0.09
    æķķ
    0.09
     dur
    0.09
    -card
    0.08
    åıł
    0.08
    第ä¸ĢåIJį
    0.08
    anko
    0.08
    çĹĽ
    0.08
    Activations Density 0.077%

    No Known Activations