© 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. 8602
    Prev
    Next
    INDEX
    Explanations

    future events and timing

    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
    å®Ľ
    -0.12
    èİ·å¾ĹæĽ´å¤ļ
    -0.10
    çķĮçļĦ
    -0.09
    塾
    -0.09
    çijķ
    -0.09
    rut
    -0.09
    aphore
    -0.09
    ала
    -0.09
    æŀĦçŃij
    -0.08
    sigmoid
    -0.08
    POSITIVE LOGITS
    ated
    0.11
    åıĮèµ¢
    0.09
    çºł
    0.09
    ATED
    0.09
     for
    0.09
    jin
    0.08
    ned
    0.08
    ë
    0.08
     populated
    0.08
    ç¨Ģ
    0.08
    Activations Density 0.022%

    No Known Activations