© 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. 57923
    Prev
    Next
    INDEX
    Explanations

    form method

    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
    ä¸ī人
    -0.10
    antar
    -0.10
    chaft
    -0.10
    доÑĢ
    -0.09
    æĹ¥çĶµ
    -0.09
    椰
    -0.08
    éļ¾æĢª
    -0.08
     coun
    -0.08
    çĻ£
    -0.08
     صاÙĦ
    -0.08
    POSITIVE LOGITS
    åIJīä»ĸ
    0.09
    äºİ
    0.09
    éĢ¸
    0.08
    åIJĦ个
    0.08
    ä¸Ģä½ĵ
    0.08
    åIJĮæł·çļĦ
    0.08
    pd
    0.08
    ï¸ı
    0.08
    äºİæѤ
    0.08
    æŁIJ个
    0.08
    Activations Density 0.206%

    No Known Activations