© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8907
    Prev
    Next
    INDEX
    Explanations

    commercial applications or works

    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
    çļĦåľ°ä½į
    -0.09
    åļ£
    -0.09
    é£ŀæī¬
    -0.09
    ermann
    -0.08
     Booker
    -0.08
     Ank
    -0.08
    éĦĤ
    -0.08
    赦
    -0.08
    ä¹ĭ声
    -0.08
    ifu
    -0.08
    POSITIVE LOGITS
    à¸Ľà¸£à¸°à¹Ĥยà¸Ĭà¸Ļ
    0.09
    è´¸
    0.09
    åı¦ä¸ĢåįĬ
    0.09
    VRT
    0.08
    女åŃ©åŃIJ
    0.08
    è±³
    0.08
    ç¿®
    0.08
    _PD
    0.08
     UIP
    0.08
     lith
    0.08
    Activations Density 0.011%

    No Known Activations