© 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. 2852
    Prev
    Next
    INDEX
    Explanations

    social groups

    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
    ä¼ģä¸ļåĴĮ
    -0.11
    æĪijåĴĮ
    -0.10
    æĸĩåĮĸåĴĮ
    -0.10
    建设åĴĮ
    -0.09
    çIJĨ解åĴĮ
    -0.09
    ç»ıéªĮåĴĮ
    -0.09
    èĥ½åĬĽåĴĮ
    -0.09
    ushman
    -0.09
     somewhere
    -0.09
    éĮ¯
    -0.09
    POSITIVE LOGITS
    éĥ½éĿŀ常
    0.08
    bone
    0.08
    /or
    0.08
    ROSS
    0.08
    ä¼Ļä¼´
    0.08
    ä¸Ģèµ·
    0.08
     genie
    0.08
    æĢ§åij½
    0.08
    ä¸ĵ享
    0.08
    .finished
    0.08
    Activations Density 0.074%

    No Known Activations