© 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. 20704
    Prev
    Next
    INDEX
    Explanations

    Neverthelss, nonetheless

    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
     zwar
    -0.16
    çĶļèĩ³è¿ĺ
    -0.14
    çļĦå°±æĺ¯
    -0.11
    çĶļèĩ³è¿ŀ
    -0.10
    åĽºçĦ¶
    -0.10
     tháºŃm
    -0.10
     thus
    -0.10
    ound
    -0.10
    è¿«ä¸įåıĬå¾ħ
    -0.10
    æĢ§å¼º
    -0.09
    POSITIVE LOGITS
     ë¶Ī구íķĺê³ł
    0.13
    æľīäºĽ
    0.10
    ez
    0.09
    è¿ĺæĺ¯è¦ģ
    0.09
    æŀĦæĪIJäºĨ
    0.09
    forth
    0.09
    è¿ĺæĺ¯ä¼ļ
    0.09
    onas
    0.09
    ä½ľä¸ºä¸Ģç§į
    0.08
    æľīä¸įå°ij
    0.08
    Activations Density 0.011%

    No Known Activations