© 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. 30542
    Prev
    Next
    INDEX
    Explanations

    resilience and determination

    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
    æ»Ķ
    -0.10
    çĨŁ
    -0.09
    社
    -0.09
    ound
    -0.08
    anza
    -0.08
    è¨Ģ论
    -0.08
    iform
    -0.08
    çĤ¹åĩ»æŁ¥çľĭ
    -0.08
    Scale
    -0.08
    pike
    -0.08
    POSITIVE LOGITS
    åĿļ飧
    0.24
    顽强
    0.24
    飧æĢ§
    0.21
    åĿļ强
    0.20
     resilience
    0.19
    æ¯ħåĬĽ
    0.19
    飧
    0.18
    åĢĶ
    0.18
     resil
    0.17
     resilient
    0.17
    Activations Density 0.074%

    No Known Activations