© 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. 20736
    Prev
    Next
    INDEX
    Explanations

    from

    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
    ropa
    -0.12
    åİĨæŶ
    -0.10
    å¼ķåĬĽ
    -0.09
    зв
    -0.09
    åĬĽè¿ĺæĺ¯
    -0.09
    uft
    -0.09
    æł¡å¤ĸ
    -0.09
    æĮĤçīĮ
    -0.09
    åºĬåŀ«
    -0.09
    ISE
    -0.09
    POSITIVE LOGITS
    管çIJĨä¸Ńå¿ĥ
    0.09
    串
    0.08
     Guar
    0.08
    é«ĺå±±
    0.08
    eos
    0.08
    å¹´å¼Ģå§ĭ
    0.08
    ordo
    0.08
    æ»ĭçĶŁ
    0.08
    æĹ¥èµ·
    0.08
     CLEAR
    0.08
    Activations Density 0.078%

    No Known Activations