© 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. 20705
    Prev
    Next
    INDEX
    Explanations

    Dubai, Abu Dhabi, Hyderabad, Emirates

    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
    ing
    -0.11
    ed
    -0.09
    lick
    -0.09
    è´¬åĢ¼
    -0.09
     legacy
    -0.09
    è¾ħ导
    -0.08
    ราว
    -0.08
    Gate
    -0.08
    æ´»è·ĥ
    -0.08
    æijĺç¼ĸ
    -0.08
    POSITIVE LOGITS
    insky
    0.10
    湫
    0.09
    adin
    0.09
     اÙĦÙĥبرÙī
    0.09
    å¿ĥæĦı
    0.09
    ClassLoader
    0.08
    _PD
    0.08
    ALTH
    0.08
    翳
    0.08
    Toolkit
    0.08
    Activations Density 0.015%

    No Known Activations