© 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. 37014
    Prev
    Next
    INDEX
    Explanations

    awards and titles

    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
    PAD
    -0.09
     Bair
    -0.09
    oya
    -0.08
    exas
    -0.08
    éĦ¢
    -0.08
    ifax
    -0.08
    <![
    -0.08
    oled
    -0.08
    ROID
    -0.07
    æĹħç¨ĭ
    -0.07
    POSITIVE LOGITS
    è®°
    0.10
    åį±
    0.10
    æĩ¦
    0.10
    å¿ĥåĬ¨
    0.10
    ä»Ģä¹Īåij¢
    0.09
    åĮºåĪĨ
    0.09
     peninsula
    0.09
    æĢľ
    0.09
    æħij
    0.09
    éħĭ
    0.09
    Activations Density 0.032%

    No Known Activations