© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60990
    Prev
    Next
    INDEX
    Explanations

    with or greater accuracy

    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
    åģļäºĭ
    -0.10
    éĢĤéĩı
    -0.10
    proper
    -0.10
    èĩŃ
    -0.09
    å¹²äºĭ
    -0.09
    lying
    -0.08
    åĸĦæĦı
    -0.08
     gib
    -0.08
    apus
    -0.08
    æł¼
    -0.08
    POSITIVE LOGITS
    åħĪæĬĬ
    0.09
    åīįæīĢæľª
    0.08
    è°ģèĥ½
    0.08
    ERY
    0.08
    é¢ĩ
    0.08
    æĬĬå®ĥ
    0.08
    ä¸įçŁ¥
    0.08
     Bravo
    0.08
    赫
    0.08
    ptic
    0.08
    Activations Density 0.045%

    No Known Activations