© 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. 57474
    Prev
    Next
    INDEX
    Explanations

    with expression

    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
    ä¼´éļıçĿĢ
    -0.09
    -peer
    -0.09
    /mit
    -0.09
    åĪ°æĿ¥
    -0.08
    æĭīçĿĢ
    -0.08
    ä¹ĥèĩ³
    -0.08
    è¿ĩ硬
    -0.08
    åĺ¿
    -0.08
    LECTION
    -0.08
     spanking
    -0.08
    POSITIVE LOGITS
    轨迹
    0.09
    judge
    0.09
    oca
    0.08
    è°²
    0.08
    otten
    0.08
    chy
    0.08
    åIJĮæł·çļĦ
    0.08
    çĵł
    0.08
    åĢ¦
    0.08
     convers
    0.08
    Activations Density 0.015%

    No Known Activations