© 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. 49175
    Prev
    Next
    INDEX
    Explanations

    second, consecutive

    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
    åģ·åģ·
    -0.10
    èĤĨ
    -0.09
    çĥģ
    -0.09
    èĦį
    -0.09
    è´¨çĸij
    -0.09
    неÑģ
    -0.09
     clos
    -0.09
     Bucks
    -0.09
    欺è¯Ī
    -0.09
    æĮ¤
    -0.09
    POSITIVE LOGITS
    æī¿è®¤
    0.16
    æİ¥åıĹ
    0.14
    è¿İ
    0.12
    让
    0.12
    妥åįı
    0.11
     accept
    0.11
    丧失
    0.11
    æİ¥åıĹäºĨ
    0.11
     accepts
    0.11
    åħģ许
    0.11
    Activations Density 0.144%

    No Known Activations