© 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. 61190
    Prev
    Next
    INDEX
    Explanations

    making a decision

    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
    湫
    -0.10
    çļĦåĬĽéĩı
    -0.09
    å¤Ļ
    -0.08
    满äºĨ
    -0.08
    æ¯ı次
    -0.08
    nbsp
    -0.08
    ender
    -0.08
    ç»ıæµİåѦ
    -0.08
    éķ¿å¤§äºĨ
    -0.08
    è¦ģ好好
    -0.08
    POSITIVE LOGITS
    ä¸Ģ代
    0.10
    sink
    0.09
    ispers
    0.09
    æľĢç»Ī
    0.09
    èįī
    0.09
    eks
    0.09
    çĪ±ç¾İ
    0.09
    çĤ¹å¤´
    0.09
    ä¿¡æīĺ
    0.08
    æĭ©
    0.08
    Activations Density 0.046%

    No Known Activations