© 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. 8815
    Prev
    Next
    INDEX
    Explanations

    addressing questions

    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
    é³ĸ
    -0.09
    åĮĸçļĦ
    -0.08
     ÑģÑĤÑĢа
    -0.08
    .Abs
    -0.08
    åijĺ
    -0.08
    ç»´æĬ¤
    -0.08
    pee
    -0.08
     Elder
    -0.08
    èįIJ
    -0.08
    TOT
    -0.08
    POSITIVE LOGITS
    追
    0.12
     questions
    0.10
    avic
    0.10
    追éĹ®
    0.09
    å¿ĥåºķ
    0.09
    干线
    0.09
    ä¸Ģ个éĹ®é¢ĺ
    0.09
    è¿Ļ个éĹ®é¢ĺ
    0.09
    èĤ´
    0.09
    çľĭçľĭ
    0.09
    Activations Density 0.395%

    No Known Activations