© 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. 33459
    Prev
    Next
    INDEX
    Explanations

    out of

    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
    iffs
    -0.10
    holds
    -0.09
    泪水
    -0.09
    æħ¢æħ¢åľ°
    -0.09
    cobra
    -0.09
    iman
    -0.09
    æĬij
    -0.09
    äºĺ
    -0.08
    åįģå¹´åīį
    -0.08
    è¿Ļç§įæĸ¹å¼ı
    -0.08
    POSITIVE LOGITS
    amp
    0.10
    èģ¿
    0.09
    TING
    0.08
    åºĶæľīçļĦ
    0.08
    ellow
    0.08
    æݥ管
    0.08
    å¿Ŀ
    0.08
    agn
    0.08
    æĬ«
    0.07
    æĽĻ
    0.07
    Activations Density 0.002%

    No Known Activations