© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37769
    Prev
    Next
    INDEX
    Explanations

    of whom

    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
    è¿Ļ件äºĭæĥħ
    -0.10
    æ§IJ
    -0.09
    欲
    -0.09
    Means
    -0.09
    scenario
    -0.09
    åįĥå¹´
    -0.09
    æ¸IJ
    -0.09
    ä¸į对
    -0.09
    -validator
    -0.09
    è¿Ļä¹Īå¤ļå¹´
    -0.08
    POSITIVE LOGITS
    大éĥ¨åĪĨ
    0.10
    æľīåĩłä¸ª
    0.09
    ä¹ĭä¸Ģ
    0.09
    alla
    0.09
    ä¸Ģ个æĺ¯
    0.08
    æľīä¸Ģ
    0.08
    éĥ½ä¼ļæľī
    0.08
    çļĦä¸Ģéĥ¨åĪĨ
    0.08
    лен
    0.08
    åħ¶ä¸Ń
    0.08
    Activations Density 0.126%

    No Known Activations