© 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. 58834
    Prev
    Next
    INDEX
    Explanations

    bonus discount

    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
    仪表
    -0.09
    xon
    -0.09
    sender
    -0.08
    éĵ£
    -0.08
     coal
    -0.08
    /root
    -0.08
    ze
    -0.08
     gut
    -0.08
    åij¨ä¸Ģ
    -0.08
    åı«æĪij
    -0.08
    POSITIVE LOGITS
    éĴ¿
    0.10
    èµı
    0.09
    aphore
    0.08
    å¿ĥåºķ
    0.08
    åľ¨æķ´ä¸ª
    0.08
    è¯Ĩ
    0.08
     Ded
    0.08
    宫
    0.08
     Doub
    0.08
    Rare
    0.08
    Activations Density 0.122%

    No Known Activations