© 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. 9228
    Prev
    Next
    INDEX
    Explanations

    cough

    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
    ÑĢод
    -0.10
     má»Ļ
    -0.10
    تÙĩ
    -0.09
    faction
    -0.09
    容è²Į
    -0.09
     Ñģобой
    -0.09
    æīĭæİĮ
    -0.09
    主ä¹ī
    -0.09
    ocrat
    -0.08
    تع
    -0.08
    POSITIVE LOGITS
    ening
    0.09
    ERM
    0.09
    iest
    0.09
    åĩ¡
    0.09
    æ¥Ķ
    0.09
    åijĽ
    0.09
    çĤ³
    0.08
    åĴ³
    0.08
    akk
    0.08
    reated
    0.08
    Activations Density 0.008%

    No Known Activations