© 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. 8381
    Prev
    Next
    INDEX
    Explanations

    speakers and presentations

    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
    /left
    -0.10
    arias
    -0.09
    åij»
    -0.09
    讥
    -0.09
     Ivan
    -0.09
    leased
    -0.09
    amber
    -0.09
    Ãłi
    -0.08
    æ®ĩ
    -0.08
    ä»»ä½ķå½¢å¼ı
    -0.08
    POSITIVE LOGITS
    åĩ¿
    0.09
    ilo
    0.09
    iline
    0.09
    manship
    0.09
     Kaw
    0.08
    lient
    0.08
    dek
    0.08
    ç³Ł
    0.08
    hips
    0.08
    elib
    0.08
    Activations Density 0.016%

    No Known Activations