© 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. 48138
    Prev
    Next
    INDEX
    Explanations

    ethical dilemmas

    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
    毫ä¸įçĬ¹è±«
    -0.08
    æħ¨
    -0.08
    è¿Ļ个æĹ¶ä»£
    -0.08
    yne
    -0.08
    æĵĴ
    -0.08
    纡
    -0.08
     offsetof
    -0.08
    åľ¨çİ°åľº
    -0.08
    亲çĪ±çļĦ
    -0.07
    佯
    -0.07
    POSITIVE LOGITS
    arius
    0.10
    grunt
    0.09
    iena
    0.09
    æij¸
    0.08
     Nicola
    0.08
    atoi
    0.08
    achel
    0.08
    hai
    0.08
    asty
    0.08
    -turned
    0.08
    Activations Density 0.625%

    No Known Activations