© 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. 4313
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in ly, ously, lessly, or gly

    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
    ä¸įå¾Ĺå·²
    -0.09
    éģIJ
    -0.09
    被迫
    -0.09
    aris
    -0.09
    æĻ°
    -0.08
    æѤåĪ»
    -0.08
    æłī
    -0.08
    ä¹ĥèĩ³
    -0.08
    é¢ĩ
    -0.08
    _DM
    -0.08
    POSITIVE LOGITS
    Ø·ÙĨ
    0.10
    å¿ĺäºĨ
    0.09
    好äºĨ
    0.09
    åĪĨæľŁ
    0.09
     Fork
    0.09
    æIJ´
    0.09
    æ·¡æ°´
    0.09
    atica
    0.09
    失åİ»äºĨ
    0.09
    nnen
    0.09
    Activations Density 0.026%

    No Known Activations