© 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. 17600
    Prev
    Next
    INDEX
    Explanations

    very different / quite different

    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
    ombat
    -0.10
    被认为æĺ¯
    -0.09
    åĬłä¸Ĭ
    -0.09
    bject
    -0.08
    alem
    -0.08
     hide
    -0.08
    æī¶
    -0.08
     catch
    -0.08
    è¦ģç´§
    -0.08
    UNT
    -0.08
    POSITIVE LOGITS
    ä¸įåIJĮçļĦ
    0.25
    ä¸įä¸Ģæł·çļĦ
    0.25
    ä¸įåIJĮäºİ
    0.21
    ä¸įä¸Ģæł·
    0.21
     different
    0.21
    æľīæīĢä¸įåIJĮ
    0.20
     diferente
    0.20
    ä¸įåIJĮ
    0.19
    éģķãģĨ
    0.18
    çļĦä¸įåIJĮ
    0.18
    Activations Density 0.164%

    No Known Activations