© 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. 28108
    Prev
    Next
    INDEX
    Explanations

    resilience and stress

    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
    unik
    -0.10
    åĨ·åį´
    -0.09
    çł»
    -0.09
    æĭĤ
    -0.09
    沧
    -0.09
     pill
    -0.09
    åĨ²åĬ¨
    -0.09
    åºıå¹ķ
    -0.09
    æł¼å±Ģ
    -0.08
     Fiesta
    -0.08
    POSITIVE LOGITS
    åģ¥åº·çļĦ
    0.13
    ä½ĵè´¨
    0.12
    çĶŁçĹħ
    0.12
    羸
    0.12
    çĶŁåij½åĬĽ
    0.11
    å¼±
    0.10
     vigor
    0.10
    èĮģ
    0.10
    åģ¥åº·
    0.10
    èĤ¥
    0.10
    Activations Density 0.141%

    No Known Activations