© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52257
    Prev
    Next
    INDEX
    Explanations

    giving power to

    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
    å²ĺ
    -0.11
    åĭ¤å¥ĭ
    -0.11
    æıŃéľ²
    -0.09
    åīįä»»
    -0.09
    ä¹ĭéģĵ
    -0.09
    éªĬ
    -0.08
    髯
    -0.08
    èĽ¾
    -0.08
    marshal
    -0.08
    ä¹ŁçŁ¥éģĵ
    -0.08
    POSITIVE LOGITS
    移
    0.10
    移åĪ°
    0.08
     Staten
    0.08
    æŀĦéĢł
    0.08
    inded
    0.08
    å±ıéļľ
    0.08
     Ùħباشر
    0.08
     Yapı
    0.08
    å¯ĵ
    0.08
    æݧåĪ¶
    0.08
    Activations Density 0.042%

    No Known Activations