© 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. 39133
    Prev
    Next
    INDEX
    Explanations

    flexible work arrangements, flexibility

    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
    åħ¬æĬ¥
    -0.09
    ä¿Ŀ温
    -0.09
    èµıæŀIJ
    -0.09
     Olson
    -0.08
    helm
    -0.08
    åŃķ
    -0.08
    Ñģкий
    -0.08
     DependencyProperty
    -0.08
    _quest
    -0.08
    èĿĩ
    -0.08
    POSITIVE LOGITS
    çģµæ´»æĢ§
    0.25
    çģµæ´»
    0.24
     flex
    0.22
     flexibility
    0.22
     flexible
    0.22
    flex
    0.21
     Flex
    0.20
    æŁĶæĢ§
    0.20
    Flex
    0.20
    .flex
    0.20
    Activations Density 0.043%

    No Known Activations