© 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. 30178
    Prev
    Next
    INDEX
    Explanations

    education, office, society, evaluation, advising

    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
    饱
    -0.10
    桧
    -0.10
    éļĪ
    -0.09
    _MUX
    -0.09
    人åĬĽ
    -0.09
    康
    -0.08
    éc
    -0.08
    纯
    -0.08
    串
    -0.08
    管çIJĨç³»ç»Ł
    -0.08
    POSITIVE LOGITS
    æĦıè¯Ĩ
    0.12
    æ·±åħ¥äººå¿ĥ
    0.11
    å®£ä¼łæ´»åĬ¨
    0.10
    çī¢è®°
    0.10
    æĦıèŃĺ
    0.10
    误åĮº
    0.09
    åIJ¬å®Į
    0.09
    éĺ²èĮĥ
    0.09
    æĻ®åıĬ
    0.09
    路人
    0.09
    Activations Density 0.138%

    No Known Activations