© 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. 50225
    Prev
    Next
    INDEX
    Explanations

    cleanliness and upkeep

    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
    anni
    -0.09
    åľĨ满
    -0.09
    ourt
    -0.08
    é«ĺ强度
    -0.08
    åħ¨è¿ĩç¨ĭ
    -0.08
    è¢ħ
    -0.08
    åŁĭ
    -0.08
    ibal
    -0.08
    pic
    -0.08
    åľĨ满å®ĮæĪIJ
    -0.08
    POSITIVE LOGITS
    å¹²åĩĢ
    0.13
    çݰ代åĮĸ
    0.11
    åħ¬çĶ¨
    0.11
    èĤ®
    0.10
     اÙĦØŃدÙĬØ«
    0.10
    æķ´æ´ģ
    0.10
    ä¼ijåģĩ
    0.09
     ÑģовÑĢем
    0.09
     modern
    0.09
    Bootstrap
    0.09
    Activations Density 0.020%

    No Known Activations