© 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. 29935
    Prev
    Next
    INDEX
    Explanations

    World Bank

    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
    ден
    -0.09
    CTION
    -0.09
    нал
    -0.09
    æºŁ
    -0.08
    glass
    -0.08
    ди
    -0.08
    ä½Ķ
    -0.08
    mani
    -0.08
    acing
    -0.08
    zet
    -0.08
    POSITIVE LOGITS
    触åıĬ
    0.09
    /right
    0.09
    æ§Ľ
    0.09
    æĻºæħ§
    0.09
    骨æĬĺ
    0.09
    æĪŁ
    0.09
    éĺµèIJ¥
    0.08
    åİĿ
    0.08
    å¤§éĽ¨
    0.08
    æĥħåķĨ
    0.08
    Activations Density 0.005%

    No Known Activations