© 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. 32557
    Prev
    Next
    INDEX
    Explanations

    vacuum cleaner parts

    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
    anka
    -0.09
    æŃ£æĺ¯
    -0.09
     tens
    -0.09
     nghi
    -0.09
    uler
    -0.08
    ClassName
    -0.08
    ä¹ŀ
    -0.08
    inki
    -0.08
    icy
    -0.08
    upd
    -0.08
    POSITIVE LOGITS
    å°ĺ
    0.10
     Legends
    0.10
    éĻ¤å°ĺ
    0.09
    塵
    0.09
    æŃ»è§Ĵ
    0.09
    åĽ¢åľĨ
    0.09
    æīĵæī«
    0.09
    æķ´é¡¿
    0.09
    çľĭä¸įåĪ°
    0.09
    çİ«çij°
    0.09
    Activations Density 0.015%

    No Known Activations