© 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. 35511
    Prev
    Next
    INDEX
    Explanations

    incentives

    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
    æĪIJçĨŁ
    -0.10
    æĪIJçĨŁçļĦ
    -0.09
    åij½
    -0.09
     prejud
    -0.09
    -drop
    -0.09
     benef
    -0.08
     mat
    -0.08
    æĬķèµĦé¢Ŀ
    -0.08
     critic
    -0.08
     Mature
    -0.08
    POSITIVE LOGITS
     incentives
    0.11
     incentive
    0.10
    诱æĥij
    0.10
    é¼ĵåĬ±
    0.10
    诱
    0.09
    縱
    0.09
    æ¿ĢåĬ±
    0.09
    å¨ĺ
    0.09
     гоÑģ
    0.08
    æģ¶æĢ§
    0.08
    Activations Density 0.040%

    No Known Activations