© 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. 63167
    Prev
    Next
    INDEX
    Explanations

    intention, purpose, deliberate

    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
    å»ĵ
    -0.11
    æĸ°å½¢åĬ¿
    -0.11
    èĢĮçİ°åľ¨
    -0.10
    ä¿¡ä»»
    -0.09
    龸
    -0.09
    ture
    -0.09
    说ä¸įå®ļ
    -0.09
    å¨ģ
    -0.09
    æĬ¥éĶĢ
    -0.09
    _mC
    -0.09
    POSITIVE LOGITS
    æľīæĦı
    0.25
    æķħæĦı
    0.22
    åĪ»æĦı
    0.22
     intentional
    0.21
     deliberate
    0.21
     intentionally
    0.20
     deliberately
    0.19
     purposely
    0.19
    çī¹æĦı
    0.16
     purpose
    0.15
    Activations Density 0.058%

    No Known Activations