© 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. 37173
    Prev
    Next
    INDEX
    Explanations

    culture change, tug-of-war, love/hate, learning curve, culture-war, gun battle, paradigm shift

    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
    èĢħãģ®
    -0.09
    æĮ£éĴ±
    -0.09
    жд
    -0.09
    æłĸ
    -0.09
    æ¦Ķ
    -0.09
     Spread
    -0.08
    .checkNotNull
    -0.08
    yne
    -0.08
    SCO
    -0.08
    èĢħ
    -0.08
    POSITIVE LOGITS
    ä»Ĺ
    0.12
    battle
    0.12
     battle
    0.11
     Battle
    0.10
     battles
    0.10
    ä¸Ģåľº
    0.10
    缼ä¼ļ
    0.10
    ä¹ĭæĪĺ
    0.10
    æĪĺäºī
    0.10
     cuá»Ļc
    0.09
    Activations Density 0.227%

    No Known Activations