© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 27888
    Prev
    Next
    INDEX
    Explanations

    human and its context

    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
    éľı
    -0.10
    ä¸Ģ个人
    -0.10
    人çĶŁçļĦ
    -0.09
    人们çļĦ
    -0.09
    cook
    -0.08
    ilia
    -0.08
    人ä½ĵ
    -0.08
    ä¸ĢåĢĭ人
    -0.08
    人们对
    -0.08
    为æ°ij
    -0.08
    POSITIVE LOGITS
    _unicode
    0.09
    åľ¨è¿ĩ渡
    0.09
    æľīæĦıæĢĿ
    0.09
    aders
    0.09
    èĴ½
    0.09
    ampil
    0.08
    phinx
    0.08
    akest
    0.08
    åľ¨åľ°ä¸Ĭ
    0.08
    æĬ¤åį«
    0.08
    Activations Density 0.034%

    No Known Activations