© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9442
    Prev
    Next
    INDEX
    Explanations

    lose or lost leading to something

    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
    åIJİæľŁ
    -0.10
    ä¸į容æĺĵ
    -0.09
    URATION
    -0.09
    åİĨåı²æĤłä¹ħ
    -0.09
     иÑģÑĤоÑĢиÑı
    -0.09
    itious
    -0.09
    è·ĭ
    -0.09
    è¿Łè¿Ł
    -0.09
    æĸ°åħ´äº§ä¸ļ
    -0.09
    trä
    -0.09
    POSITIVE LOGITS
     sight
    0.11
    fully
    0.10
    æİī
    0.10
     control
    0.09
    çĦ¦çĤ¹
    0.09
    æĸ¹åIJij
    0.09
     faith
    0.09
    iders
    0.09
    æİīäºĨ
    0.09
    çĪº
    0.08
    Activations Density 0.034%

    No Known Activations