© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36887
    Prev
    Next
    INDEX
    Explanations

    companies, organizations, institution

    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
    æ¯ıä¸Ģä½į
    -0.10
    æĺ¯ä¸Ģä½į
    -0.10
    æľīä¸Ģä½į
    -0.09
    åĭŁ
    -0.08
    asher
    -0.08
    æĺ¯ä¸ĢåIJį
    -0.08
    èĺĩ
    -0.08
    å¿ĥè·³
    -0.08
     EACH
    -0.08
    èĭı
    -0.08
    POSITIVE LOGITS
    LOCKS
    0.10
    侬
    0.09
    çĹħæ¯ĴæĦŁæŁĵ
    0.09
    ystems
    0.09
    éķ¿çŁŃ
    0.09
    ksen
    0.09
    çĶµåŃIJä¿¡æģ¯
    0.08
    æŀª
    0.08
     pne
    0.08
    _DEVICES
    0.08
    Activations Density 0.116%

    No Known Activations