© 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. 37874
    Prev
    Next
    INDEX
    Explanations

    negation of reported details or 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
    èľ¡
    -0.09
    aling
    -0.09
    ç§ijæĬĢèĤ¡ä»½
    -0.08
    INA
    -0.08
     Bik
    -0.08
     conj
    -0.08
    æķ°çłģ
    -0.08
    çķ¥å¾®
    -0.08
    åıªéľĢ
    -0.08
    ServerError
    -0.08
    POSITIVE LOGITS
    è¿ĩå¾Ģ
    0.10
    æĸ¼æĺ¯
    0.09
    äºİæĺ¯
    0.09
    otropic
    0.08
    çıį
    0.08
    伤亡
    0.08
    èĤĩ
    0.08
     наÑĢ
    0.08
     Rout
    0.08
    人身
    0.08
    Activations Density 0.029%

    No Known Activations