© 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. 2044
    Prev
    Next
    INDEX
    Explanations

    ability to

    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
    åĬĽæ±Ĥ
    -0.11
    è¯ķåĽ¾
    -0.10
    è¸Ĭè·ĥ
    -0.10
    agged
    -0.10
    emode
    -0.10
    å°Ŀè¯ķ
    -0.10
     kans
    -0.10
    åı¯è§ģ
    -0.09
    maal
    -0.09
    ATAB
    -0.09
    POSITIVE LOGITS
    èĥľä»»
    0.09
    æģ«
    0.09
    ify
    0.08
    ä»»ä½ķå½¢å¼ı
    0.08
    éļĶçĿĢ
    0.08
    å¿į
    0.08
    æ¯ķç«Łæĺ¯
    0.08
    çĪ¬ä¸Ĭ
    0.08
    让人
    0.08
    ç¥ĸ
    0.08
    Activations Density 0.112%

    No Known Activations