© 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. 30061
    Prev
    Next
    INDEX
    Explanations

    river and tributary

    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
    cies
    -0.08
    åıĭæĥħéĵ¾æİ¥
    -0.08
     Javier
    -0.08
    åĭī
    -0.08
    æįŁå®³
    -0.08
    ä¼ģ
    -0.08
    æ¼ı
    -0.08
    è¹Ĵ
    -0.08
    ayers
    -0.07
     spe
    -0.07
    POSITIVE LOGITS
    æ²³æµģ
    0.15
    åĪĨæĶ¯
    0.13
     trib
    0.13
    æĶ¯
    0.12
    河水
    0.12
    æ²³éģĵ
    0.12
     river
    0.12
     River
    0.11
    æ²³
    0.11
     sông
    0.11
    Activations Density 0.176%

    No Known Activations