© 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. 36964
    Prev
    Next
    INDEX
    Explanations

    that good

    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
    æĪª
    -0.09
     defaultProps
    -0.09
    ä¸įå®ľ
    -0.09
    2
    -0.08
    4
    -0.08
    6
    -0.08
    رة
    -0.08
    8
    -0.08
    9
    -0.08
    7
    -0.08
    POSITIVE LOGITS
    å®ŀåľ¨å¤ª
    0.14
    å®ŀåľ¨æĺ¯å¤ª
    0.13
    è¿Ļä¹Īå¤ļ
    0.11
    åĽłä¸ºä»ĸ们
    0.10
    è¿ĻèĪ¬
    0.10
    åĩĨ
    0.10
    uen
    0.10
    å¦ĤæѤ
    0.10
    seudo
    0.10
    è¿Ļä¹Ī
    0.10
    Activations Density 0.044%

    No Known Activations