© 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. 51601
    Prev
    Next
    INDEX
    Explanations

    alternative to conventional

    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
    èĢĮä¸įæĺ¯
    -0.12
    èĢĮéĿŀ
    -0.09
    ba
    -0.09
     rather
    -0.09
    没éĶĻ
    -0.08
    éĩĩ访æŶ
    -0.08
     chứ
    -0.08
     vind
    -0.08
     grac
    -0.08
    çīµ
    -0.08
    POSITIVE LOGITS
    常è§Ħ
    0.12
    åħ¶ä»ĸ
    0.12
    åħ¶ä»ĸçļĦ
    0.12
    ä»»ä½ķ
    0.12
     سÙĪÙī
    0.11
     other
    0.11
    寻常
    0.11
    ä»ĸãģ®
    0.11
    ä»»ä½ķä¸Ģ个
    0.10
    åħ¶ä»ĸ人
    0.10
    Activations Density 0.089%

    No Known Activations