© 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. 9488
    Prev
    Next
    INDEX
    Explanations

    explaining why something is

    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
    èģĶç³»çĶµè¯Ŀ
    -0.09
    æİĤ
    -0.09
    EFR
    -0.09
    çľĭä¸Ģçľĭ
    -0.08
    èı±
    -0.08
    çĭ·
    -0.08
    apons
    -0.08
    /o
    -0.08
     acquaintance
    -0.08
    erty
    -0.08
    POSITIVE LOGITS
    éĹ¹
    0.08
    说æĪij
    0.08
    说ä»Ģä¹Ī
    0.08
    æĪijä»¬åľ¨
    0.08
     itself
    0.08
    ä½łè¦ģ
    0.08
    æĥ³åĪ°
    0.08
    éļ¾æĢª
    0.08
    å¿ĥæĦ¿
    0.07
     minds
    0.07
    Activations Density 0.029%

    No Known Activations