© 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. 9198
    Prev
    Next
    INDEX
    Explanations

    expeditionary, expedients, expedited

    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
    说æĺ¯
    -0.10
    ague
    -0.09
    ifest
    -0.09
    ayer
    -0.09
    ning
    -0.09
    åĽ½å®ī
    -0.09
    çĽħ
    -0.09
    éªĸ
    -0.08
    æĺ¯ä¸Ģ座
    -0.08
    zelf
    -0.08
    POSITIVE LOGITS
    ively
    0.11
    naire
    0.10
    ally
    0.09
    ç½ijå°ıç¼ĸ
    0.09
    zend
    0.09
    íĴĪ
    0.09
    ordinary
    0.09
    aqu
    0.09
    ilha
    0.09
    Reusable
    0.09
    Activations Density 0.006%

    No Known Activations