© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38392
    Prev
    Next
    INDEX
    Explanations

    negative events and incidents

    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
     Ñģами
    -0.09
    ral
    -0.09
    ulty
    -0.08
    æļ´åĬĽ
    -0.08
    å¥ĹæĪ¿
    -0.08
    ODB
    -0.08
    çī¢è®°
    -0.08
    京
    -0.08
    ascade
    -0.08
    reck
    -0.08
    POSITIVE LOGITS
    é¢ĺæĿIJ
    0.09
    CELL
    0.09
    å¿Ļ
    0.08
    èıĬèĬ±
    0.08
     Elm
    0.08
     Colo
    0.08
     ÑĤепло
    0.08
    æħ°
    0.08
    Slim
    0.08
    åĺ¿åĺ¿
    0.08
    Activations Density 0.146%

    No Known Activations