© 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. 51551
    Prev
    Next
    INDEX
    Explanations

    yet, anymore, again

    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
    侥幸
    -0.11
    èī¯
    -0.10
    é¡·
    -0.09
    äºĺ
    -0.09
    æĿ¥åģļ
    -0.09
    æľīæľºä¼ļ
    -0.08
    aker
    -0.08
    ç»´æĿĥ
    -0.08
    emann
    -0.08
    prite
    -0.08
    POSITIVE LOGITS
     SEQ
    0.09
    çĿ¦
    0.08
    _prefs
    0.08
    åĵªäºĽ
    0.08
    nis
    0.08
    cle
    0.08
    飧æĢ§
    0.08
    åĪĩãĤĮ
    0.08
    .processor
    0.08
    ä¹łæĥ¯
    0.08
    Activations Density 0.060%

    No Known Activations