© 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. 37313
    Prev
    Next
    INDEX
    Explanations

    commands for input

    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
    åı£è¢ĭ
    -0.10
    è¿Ļä¸ĢçĤ¹
    -0.09
    森
    -0.09
     пиÑĤ
    -0.09
    ãģĿãĤĮãĤĴ
    -0.09
    .Void
    -0.09
    åħ¬åı¸åľ¨
    -0.09
    ÑĢин
    -0.09
    æĦıåij³çĿĢ
    -0.09
    astered
    -0.09
    POSITIVE LOGITS
    åŃļ
    0.09
    ä¸Ģ头
    0.09
     Richie
    0.09
    ä¸ĸ家
    0.08
     dein
    0.08
    åģ·åģ·
    0.08
    éĴŃ
    0.08
    åħ¼èģĮ
    0.08
    åĪĴåĪĨ
    0.08
    æľīä¸Ģä½į
    0.08
    Activations Density 0.048%

    No Known Activations