© 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. 20475
    Prev
    Next
    INDEX
    Explanations

    came to be

    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
    éĺī
    -0.10
    æ¹Ľ
    -0.10
    اء
    -0.09
     ë°Ķë¡ľ
    -0.09
    æĹłè¾ľ
    -0.09
    è¿Ļ让
    -0.09
    èĬŃ
    -0.09
    kest
    -0.09
    ialog
    -0.09
    &w
    -0.08
    POSITIVE LOGITS
    æĪIJ为
    0.14
     becoming
    0.13
    æĪIJ为äºĨ
    0.12
    æĪIJçĤº
    0.12
    æĪIJäºĨ
    0.12
     becomes
    0.10
     became
    0.10
     become
    0.10
    åıĺå¾Ĺ
    0.10
    åıĺæĪIJ
    0.10
    Activations Density 0.041%

    No Known Activations