© 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. 19240
    Prev
    Next
    INDEX
    Explanations

    regardless of whether

    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¡·
    -0.10
    å½ĵä¹ĭæĹłæĦ§
    -0.09
    бÑĥÑĢ
    -0.09
    brook
    -0.09
    ãģ¹ãģį
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    çİĸ
    -0.09
    ä¼½
    -0.08
    -runtime
    -0.08
    .trade
    -0.08
    POSITIVE LOGITS
    æľīå¤ļä¹Ī
    0.10
    åħ¶ä»ĸ
    0.10
    åѬ
    0.09
     Plenty
    0.09
    æĺ¯åIJ¦
    0.09
    æľªå¿ħ
    0.09
    ä¸įä¸Ģå®ļ
    0.09
    ä¹Łä¸įè¦ģ
    0.09
    æľī人
    0.09
    æľīå¤ļå°ij
    0.09
    Activations Density 0.122%

    No Known Activations