© 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. 8425
    Prev
    Next
    INDEX
    Explanations

    of or poor

    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
    åĽłä¸ºä½ł
    -0.09
    çľĭä½ł
    -0.09
    è¶Ĭ
    -0.09
    _RA
    -0.09
    æķ´æĶ¹æݪæĸ½
    -0.09
    åįģåĩłä¸ª
    -0.09
    æĿĤ
    -0.09
    ä½łåĸľæ¬¢
    -0.09
    èĢ¦
    -0.09
    æ±²åıĸ
    -0.08
    POSITIVE LOGITS
    yen
    0.10
    å¼Ł
    0.09
    adel
    0.09
     accom
    0.09
     conserv
    0.09
     of
    0.09
     conservative
    0.09
    ãĥ¡ãĥĥ
    0.08
    èĮĤ
    0.08
    reen
    0.08
    Activations Density 0.065%

    No Known Activations