© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58917
    Prev
    Next
    INDEX
    Explanations

    lifetime warranties, achievement, expectancy, partner

    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
    èĶĹ
    -0.08
    ä¸ĸ家
    -0.08
    äºĽä»Ģä¹Ī
    -0.08
    æ¥Ŀ
    -0.08
    ãģ¤ãģĦ
    -0.07
    antine
    -0.07
    оÑģоб
    -0.07
    down
    -0.07
    at
    -0.07
    ifice
    -0.07
    POSITIVE LOGITS
    åĺĺ
    0.10
    ä¸Ģå®ļçļĦ
    0.10
    theless
    0.10
    mente
    0.10
    ä¸Ģçīĩ
    0.09
    lane
    0.09
    ilty
    0.09
    ittest
    0.09
    ä¸Ģéĥ¨
    0.09
    ä¸Ģè´¯
    0.09
    Activations Density 0.012%

    No Known Activations