© 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. 10738
    Prev
    Next
    INDEX
    Explanations

    php copyright notices

    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
    çłĮ
    -0.09
    æķŀå¼Ģ
    -0.09
    oya
    -0.08
    åIJĮä»ģ
    -0.08
    iez
    -0.08
    缸åħ³æĸ°éĹ»
    -0.08
    综
    -0.08
    resco
    -0.08
    åĢ«
    -0.08
     дол
    -0.08
    POSITIVE LOGITS
    æĽĿ
    0.10
    ®
    0.09
    åĮª
    0.09
    åľŃ
    0.09
    åĹª
    0.09
    械
    0.08
    ®,
    0.08
     благ
    0.08
    uits
    0.08
    éŃĶçİĭ
    0.08
    Activations Density 0.002%

    No Known Activations