© 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. 17089
    Prev
    Next
    INDEX
    Explanations

    concessions

    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
    åįĬ个
    -0.10
    æIJ¬
    -0.09
    åĩ«
    -0.09
    ä¸įå¦Ĥ
    -0.09
    ä¸įåıĬ
    -0.09
    æĢľ
    -0.09
    ä¸ĢèĪ¬äºº
    -0.08
     ×ķ×IJ×Ļף
    -0.08
     lesser
    -0.08
    orts
    -0.08
    POSITIVE LOGITS
    åį´æĺ¯
    0.16
    åį´
    0.13
    åį»
    0.12
     nonetheless
    0.12
     полно
    0.11
    åį´è¢«
    0.11
     nevertheless
    0.10
    足以
    0.10
    åĢĴæĺ¯
    0.10
    æīĵå¾Ĺ
    0.09
    Activations Density 0.104%

    No Known Activations