© 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. 27416
    Prev
    Next
    INDEX
    Explanations

    numbers, roman, americans, workers, rhode

    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
    éĥ¨ä½į
    -0.09
    ä¸ºæľŁ
    -0.09
    妣
    -0.09
    omy
    -0.09
    æĹģè¾¹çļĦ
    -0.09
    åıĪ被
    -0.09
    丰ç¡ķ
    -0.09
    رض
    -0.09
    让æ¶Īè´¹èĢħ
    -0.09
    ipment
    -0.08
    POSITIVE LOGITS
    éģįå¸ĥ
    0.11
    åŃĺéĩı
    0.10
    æ´»è·ĥ
    0.10
    åħ±æľī
    0.10
     currently
    0.10
    æ³ķå®ļ
    0.09
    åįĩéĻį
    0.09
    缮åīį
    0.09
    åĤ¨å¤ĩ
    0.09
    幸
    0.09
    Activations Density 0.127%

    No Known Activations