© 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. 55935
    Prev
    Next
    INDEX
    Explanations

    engage in activities

    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
    avit
    -0.10
    æĭĻ
    -0.09
    æĭ¨
    -0.09
    æĵĺ
    -0.09
    adem
    -0.09
    æĴŃ
    -0.08
    ä¿¡å¿ĥ
    -0.08
    .fail
    -0.08
    æĤĦæĤĦ
    -0.08
    åīįçŀ»
    -0.08
    POSITIVE LOGITS
    edException
    0.10
    ä»»ä½ķ人
    0.10
    çĦ¶
    0.10
    åĥı个
    0.09
    æĿ¥å½¢å®¹
    0.09
    fully
    0.09
    å¤ļä½į
    0.08
    USTER
    0.08
    广大
    0.08
    çļĦæĢ§æł¼
    0.08
    Activations Density 0.006%

    No Known Activations