© 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. 39736
    Prev
    Next
    INDEX
    Explanations

    curious and curiosity

    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
    _FMT
    -0.11
    æĹłäºº
    -0.09
    水管
    -0.09
    稷
    -0.09
    ä¼ĺ
    -0.09
     Canyon
    -0.08
    sports
    -0.08
    ãĤ±ãĤ¢
    -0.08
    OLS
    -0.08
    enson
    -0.08
    POSITIVE LOGITS
    好å¥ĩ
    0.30
    好å¥ĩå¿ĥ
    0.29
     curiosity
    0.29
     curious
    0.21
    æĥ³çŁ¥éģĵ
    0.19
    æĦŁåħ´è¶£çļĦ
    0.18
    æĦŁåħ´è¶£
    0.17
     инÑĤеÑĢеÑģ
    0.16
    åħ´è¶£
    0.16
     interest
    0.16
    Activations Density 0.084%

    No Known Activations