© 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. 6496
    Prev
    Next
    INDEX
    Explanations

    love, enjoyment, happiness, liking

    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
    è¾Ľ
    -0.10
    æľīä¸Ģ天
    -0.09
    èį¼
    -0.09
    éķ¿éķ¿
    -0.09
    oded
    -0.09
    kel
    -0.09
    ocha
    -0.08
    ãģıãģªãģ£ãģŁ
    -0.08
    æ¨Ĺ
    -0.08
     ÑĢеÑĪа
    -0.08
    POSITIVE LOGITS
    ä¹IJ
    0.11
    æ§ģ
    0.10
    éĥ½åĸľæ¬¢
    0.10
    æĸ°é¢ĸ
    0.10
    çī¹åĪ«
    0.10
    æ¨Ĥ
    0.09
    æī§
    0.09
    éĥ½å¾Ī
    0.09
     incentive
    0.09
    å¾Īåĸľæ¬¢
    0.09
    Activations Density 0.180%

    No Known Activations