© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7267
    Prev
    Next
    INDEX
    Explanations

    Stanford University

    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
    幺
    -0.09
    dag
    -0.09
    bitset
    -0.08
    tings
    -0.08
    cola
    -0.08
     opp
    -0.08
    ç§ijæķĻ
    -0.08
    ality
    -0.08
    nier
    -0.08
    rier
    -0.08
    POSITIVE LOGITS
     Arabia
    0.11
    é³ħ
    0.10
    shire
    0.10
    azzi
    0.09
    æĪijè¿ĺæĺ¯
    0.09
     dioxide
    0.09
    yla
    0.09
    å¨ħ
    0.09
    åĩºæīĭ
    0.09
    çıª
    0.09
    Activations Density 0.018%

    No Known Activations