© 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. 48129
    Prev
    Next
    INDEX
    Explanations

    and verb

    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
    æĸ¹æīį
    -0.10
    å¾Īå¤ļ人éĥ½
    -0.09
    çĶļèĩ³æĺ¯
    -0.09
     indeed
    -0.09
    åĪļæīį
    -0.09
    çªĹåı£
    -0.09
    ä¹ĥèĩ³
    -0.08
    çŁ¥éģĵäºĨ
    -0.08
    çªĺ
    -0.08
    éĥ½å·²ç»ı
    -0.08
    POSITIVE LOGITS
    åIJ¬åIJ¬
    0.11
    çĪ±ä½ł
    0.10
    è®°ä½ı
    0.09
    ÐIJÐĿ
    0.09
    ural
    0.09
    	TokenName
    0.09
    åĬ¡å¿ħ
    0.09
    çľĭçľĭ
    0.09
    ä¸įè¦ģ
    0.08
    layın
    0.08
    Activations Density 0.046%

    No Known Activations