© 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. 8723
    Prev
    Next
    INDEX
    Explanations

    series car prices

    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
    æĶ¶çº³
    -0.10
    毽
    -0.10
    æĭ£
    -0.10
    念
    -0.09
    æľ¬å½ĵ
    -0.08
    æµĨ
    -0.08
    æīĪ
    -0.08
    inality
    -0.08
    çªį
    -0.08
    çı
    -0.08
    POSITIVE LOGITS
    åĪ¨
    0.11
    :;↵
    0.09
     Wool
    0.09
    飨
    0.09
    ãĤ¢ãĥ¼
    0.09
    糸
    0.09
     Irving
    0.08
    Keywords
    0.08
    ho
    0.08
    upro
    0.08
    Activations Density 0.068%

    No Known Activations