© 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. 8471
    Prev
    Next
    INDEX
    Explanations

    against or rebellious

    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
    ç¾ŀ
    -0.09
    鼶ç¢İ
    -0.08
    hole
    -0.08
    è´¿
    -0.08
    éĺª
    -0.08
     Voy
    -0.08
    åĿļå®ļä¸į移
    -0.08
    æ°´å¹³
    -0.08
    way
    -0.08
     PCR
    -0.08
    POSITIVE LOGITS
    ä¸įå·²
    0.12
    èĢħçļĦ
    0.12
    åıįæĬĹ
    0.10
    -ending
    0.10
    ench
    0.10
    è¶Ĭ大
    0.10
    ä¸įçĦ¶
    0.10
     дÑĥÑħ
    0.09
     against
    0.09
     Against
    0.09
    Activations Density 0.017%

    No Known Activations