© 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. 11246
    Prev
    Next
    INDEX
    Explanations

    Easter celebrations

    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
    è°Ĺ
    -0.12
    æľ¬è½®
    -0.12
    Summon
    -0.10
    澪
    -0.10
    èĦIJ
    -0.10
    亲çĪ±
    -0.10
    ä¸Ģç§Ĵ
    -0.10
    æļijæľŁ
    -0.09
    è¿Ļè¾ĪåŃIJ
    -0.09
    çijķ
    -0.09
    POSITIVE LOGITS
    åīįå¤ķ
    0.14
    æľŁéĹ´
    0.13
    ä¹ĭéĻħ
    0.12
    è¿ĩåIJİ
    0.12
    æŶèĬĤ
    0.10
    éĤ£å¤©
    0.09
     eve
    0.09
    å±Ĭ
    0.09
    /Linux
    0.08
    æĿ¥ä¸´
    0.08
    Activations Density 0.054%

    No Known Activations