© 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. 17580
    Prev
    Next
    INDEX
    Explanations

    recording and media creation

    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
    ä¾į
    -0.10
     Tall
    -0.09
    ISTS
    -0.09
    éĹ»è¨Ģ
    -0.09
    æŀIJ
    -0.09
    åģļä¸įåĪ°
    -0.09
    羸
    -0.09
    å±ķåĩº
    -0.08
    _print
    -0.08
    Printer
    -0.08
    POSITIVE LOGITS
    å½ķåĪ¶
    0.13
    æĭįæijĦ
    0.11
    éħįéŁ³
    0.11
    éĥİ
    0.11
    åĪ¶ä½ľ
    0.10
    æľĹ
    0.10
    åīª
    0.10
    åIJĪæł¼
    0.09
    è£½ä½ľ
    0.09
    çľŁäºº
    0.09
    Activations Density 0.074%

    No Known Activations