© 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. 53494
    Prev
    Next
    INDEX
    Explanations

    latest news or updates

    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
    ureau
    -0.10
    Jet
    -0.09
    logan
    -0.08
    jet
    -0.08
    asse
    -0.08
    pta
    -0.08
    æ¬Ħ
    -0.08
    ÑĤин
    -0.08
    ä»Ĭ天æĪij们
    -0.08
    riage
    -0.07
    POSITIVE LOGITS
    ä¼Ļ
    0.08
    夹
    0.08
    åĢĵ
    0.08
    缼
    0.08
    æŃĩ
    0.08
    ront
    0.08
    çIJĨ解åĴĮ
    0.08
    æѤæĸĩ
    0.08
    缮
    0.08
    egative
    0.08
    Activations Density 0.010%

    No Known Activations