© 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. 36247
    Prev
    Next
    INDEX
    Explanations

    strategy and execution

    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
    èı²å°Ķ
    -0.09
    ä½ķåĨµ
    -0.09
    ued
    -0.09
     COPYING
    -0.09
    çĪ±
    -0.09
    éķĿ
    -0.08
    æĻºåºĵ
    -0.08
    æIJŀ好
    -0.08
    大å®Ĺ
    -0.08
    енд
    -0.08
    POSITIVE LOGITS
    为ä¹ĭ
    0.15
    ç»ĨåĮĸ
    0.14
    å®ŀçİ°
    0.12
     implementation
    0.11
     Implementation
    0.11
    åı¯è¡ĮæĢ§
    0.11
    æī§è¡Į
    0.11
     ÙĦتØŃÙĤÙĬÙĤ
    0.11
     execution
    0.11
     اÙĦتÙĨÙģÙĬ
    0.11
    Activations Density 0.125%

    No Known Activations