© 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. 18768
    Prev
    Next
    INDEX
    Explanations

    government organizations and institutions

    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
    äºĨä»ĸçļĦ
    -0.09
    æĺ¯ä¸Ģä½į
    -0.09
    omid
    -0.09
     ЧеÑĢ
    -0.08
    è¿Ľå±ķæĥħåĨµ
    -0.08
    æĺ¯ä¸ĢåIJį
    -0.08
    Cascade
    -0.08
    éĥ½æĺ¯éĿŀ常
    -0.08
     конкÑĥÑĢÑģ
    -0.08
     Hague
    -0.08
    POSITIVE LOGITS
    æľ¬èº«
    0.09
    uffers
    0.09
    éħ©
    0.09
    æľ¬èº«çļĦ
    0.09
    ngr
    0.09
    lical
    0.09
    å·¥ä½ľäººåijĺ
    0.09
    agger
    0.09
    æĺķ
    0.09
    大海
    0.08
    Activations Density 0.163%

    No Known Activations