© 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. 37029
    Prev
    Next
    INDEX
    Explanations

    uses the

    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
    Ñĩе
    -0.09
    trail
    -0.09
    à¸ŀวà¸ģ
    -0.09
    umidity
    -0.09
    utilities
    -0.09
    åħ¶ä¸ŃåĮħæĭ¬
    -0.09
    æĪij们ä¼ļ
    -0.09
    getc
    -0.09
    æĬĬå®ĥ
    -0.09
    _pod
    -0.08
    POSITIVE LOGITS
    æľĢå¤ļçļĦ
    0.11
    è¿Ļç§įæĸ¹å¼ı
    0.09
    3
    0.09
    6
    0.09
    7
    0.09
    4
    0.09
    çī¹æ®ĬçļĦ
    0.09
    çļĦæĺ¯
    0.09
    åIJĮæł·çļĦ
    0.09
    fi
    0.08
    Activations Density 0.162%

    No Known Activations