© 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. 58069
    Prev
    Next
    INDEX
    Explanations

    proceed to

    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
    è¡įçĶŁ
    -0.10
    åħ¨æĸ°çļĦ
    -0.09
    åŀ«
    -0.09
    åĤĢ
    -0.09
    橱
    -0.09
    cade
    -0.09
    æĭĤ
    -0.09
    é¦ı
    -0.09
    ä½°
    -0.09
    ä¸įç»ı
    -0.09
    POSITIVE LOGITS
    çī§
    0.09
    说èĩªå·±
    0.09
    tl
    0.08
    (Print
    0.08
    çīĽ
    0.08
    æĪijçĪ±ä½ł
    0.08
    ä¸Ģè·¯
    0.08
    arton
    0.08
    orz
    0.07
    æ¡Ĩ
    0.07
    Activations Density 0.178%

    No Known Activations