© 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. 20574
    Prev
    Next
    INDEX
    Explanations

    Little Rock, Arkansas, and surrounding areas

    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
    æķ´çIJĨ
    -0.10
    ç¾İçļĦ
    -0.09
    ç¦ıåĪ©
    -0.09
    ually
    -0.09
    ä¸Ĭæ±½
    -0.09
    毡
    -0.09
    çł´äº§
    -0.08
    å·²ä¹ħçļĦ
    -0.08
    åĽ¢éķ¿
    -0.08
    ç¾İåĮĸ
    -0.08
    POSITIVE LOGITS
    оÑģоб
    0.10
    lr
    0.09
    åīįè¿Ľ
    0.09
    .pic
    0.09
    aise
    0.08
    寻
    0.08
    edin
    0.08
    ariat
    0.08
    bearer
    0.08
    å°±åĮ»
    0.08
    Activations Density 0.001%

    No Known Activations