© 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. 55191
    Prev
    Next
    INDEX
    Explanations

    free peoples

    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
    æ³Ľ
    -0.09
    çijŃ
    -0.08
    京åŁİ
    -0.08
    æ»ĭ
    -0.08
    ista
    -0.08
    NT
    -0.08
    ians
    -0.08
    æĶ¶çĽĬçİĩ
    -0.08
    ho
    -0.08
    樵
    -0.08
    POSITIVE LOGITS
    åħħåĪĨåıijæĮ¥
    0.09
    æ§İ
    0.09
    å¹³çŃī
    0.09
    飽
    0.09
    liner
    0.09
    é«ĺæķĪçļĦ
    0.09
    é®
    0.08
    ä¸Ģç±»
    0.08
    ä¸į好
    0.08
    ÑıÑĤ
    0.08
    Activations Density 0.042%

    No Known Activations