© 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. 20405
    Prev
    Next
    INDEX
    Explanations

    individual equitable

    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
    磾
    -0.10
    éªĽ
    -0.08
    cla
    -0.08
    blings
    -0.08
    Render
    -0.08
    ÑıÑģ
    -0.08
    clamp
    -0.08
    éĦ¢
    -0.08
    ä»Ĥ
    -0.08
    è¿Ń
    -0.07
    POSITIVE LOGITS
    çįł
    0.09
    å°ıå¿ĥ
    0.09
    åĪ©çĶ¨æĤ¨çļĦ
    0.09
    éļľ
    0.09
     Wend
    0.09
     Matthias
    0.09
    å¸ĤæķĻèĤ²
    0.08
    å¢
    0.08
    çĶŁåĬ¨
    0.08
    çĬ¶æĢģä¸ĭ
    0.08
    Activations Density 0.071%

    No Known Activations