© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51203
    Prev
    Next
    INDEX
    Explanations

    opinions on events

    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
    æĪij
    -0.10
    èµ·æĿ¥
    -0.09
     вне
    -0.09
    omi
    -0.09
    举缣
    -0.09
    æĮĩçĶ²
    -0.08
     asn
    -0.08
    ickets
    -0.08
    æĪij说
    -0.08
    干货
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īæĺ¯
    0.11
     how
    0.10
    ä»Ģä¹Īåı«
    0.09
    å¦Ĥä½ķ
    0.09
     why
    0.09
     events
    0.09
    为ä½ķ
    0.08
    ç§įç§į
    0.08
    onet
    0.08
    该å¦Ĥä½ķ
    0.08
    Activations Density 0.038%

    No Known Activations