© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20629
    Prev
    Next
    INDEX
    Explanations

    years and decades ago or later

    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
    oky
    -0.09
    itte
    -0.09
    两年
    -0.09
     sem
    -0.09
    è¿ĩåĪĨ
    -0.09
    桧
    -0.08
    elly
    -0.08
    umps
    -0.08
    èĴ¿
    -0.08
     Bearing
    -0.08
    POSITIVE LOGITS
    -old
    0.10
    æĶ¹éĿ©å¼ĢæĶ¾
    0.10
    zÄħ
    0.08
    æŃ»è§Ĵ
    0.08
    大åºĨ
    0.08
    ä¿ħ
    0.08
    NAS
    0.08
    æݥ纳
    0.08
    ntax
    0.08
    friend
    0.08
    Activations Density 0.043%

    No Known Activations