© 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. 6711
    Prev
    Next
    INDEX
    Explanations

    is necessary

    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
    深深
    -0.09
    å°±å¤ŁäºĨ
    -0.09
    å·²ç»ıæľīäºĨ
    -0.09
    æ¶īå«Į
    -0.08
    hue
    -0.08
    å·²ç»ıæĪIJ为
    -0.08
    åį´è¢«
    -0.08
     доволÑĮ
    -0.08
    æľīçļĦ人
    -0.08
    èĩªåıij
    -0.08
    POSITIVE LOGITS
    æľīå¿ħè¦ģ
    0.18
     важно
    0.11
    ä¸į妨
    0.11
     необÑħодимо
    0.10
     нÑĥжно
    0.10
    åĬ³
    0.10
     faut
    0.09
     можно
    0.09
    æį
    0.09
    åĬ¡å¿ħ
    0.09
    Activations Density 0.141%

    No Known Activations