© 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. 48089
    Prev
    Next
    INDEX
    Explanations

    leaves for a place

    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
    纯粹
    -0.10
    æ¤IJ
    -0.09
    å¼ı
    -0.09
    chair
    -0.09
    çĤķ
    -0.09
    itu
    -0.09
    两端
    -0.09
    amentos
    -0.09
    èĮĥæĸĩ
    -0.09
    ridge
    -0.08
    POSITIVE LOGITS
    åľ¨åĽ½å¤ĸ
    0.10
    annon
    0.10
    åĮ¿
    0.10
    éĢĥ
    0.10
    è·ijåĪ°
    0.10
    è¾Ĺ转
    0.09
    åĮ¿åIJį
    0.09
    éĢĥèĦ±
    0.09
    ç®Ń
    0.09
    æĭ¦æĪª
    0.09
    Activations Density 0.064%

    No Known Activations