© 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. 1883
    Prev
    Next
    INDEX
    Explanations

    wealth, success, and growth

    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´¨
    -0.10
    ÑĢаÑģ
    -0.10
    ort
    -0.10
    yard
    -0.09
    orta
    -0.09
    åŃIJéĩĮ
    -0.09
    æĢ¯
    -0.09
    OLS
    -0.09
    çĹ´è¿·
    -0.09
    è·¸
    -0.08
    POSITIVE LOGITS
    ively
    0.13
    eur
    0.12
    æĻ¯è±¡
    0.11
    å·²ä¹ħ
    0.10
    fully
    0.10
    å·²ä¹ħçļĦ
    0.10
    æĺĮ
    0.09
    -minded
    0.09
    crast
    0.09
     wee
    0.09
    Activations Density 0.004%

    No Known Activations