© 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. 19124
    Prev
    Next
    INDEX
    Explanations

    no [abstract noun] whatsoever

    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
    çļĦä¸ĢäºĽ
    -0.09
    rather
    -0.09
     rather
    -0.09
    åĬĽéĩı
    -0.09
    arth
    -0.09
    rose
    -0.09
    èĢĮä¸įæĺ¯
    -0.08
    IU
    -0.08
    ç§įç§į
    -0.08
    åIJĦ个çݯèĬĤ
    -0.08
    POSITIVE LOGITS
     whatsoever
    0.20
    æľīä»»ä½ķ
    0.17
     سÙĪÙī
    0.15
     WHATSOEVER
    0.14
    ä»»ä½ķ人
    0.12
    ä¸Ŀ毫
    0.12
     há»ģ
    0.11
     вообÑīе
    0.11
    à¹Ģลย
    0.10
    çIJĨä¼ļ
    0.10
    Activations Density 0.131%

    No Known Activations