© 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. 36763
    Prev
    Next
    INDEX
    Explanations

    как phrase

    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
    ouv
    -0.10
    ãģ©
    -0.10
    anth
    -0.10
    elay
    -0.09
    дÑĥм
    -0.09
    è§Ĵ
    -0.09
     likes
    -0.09
    åıijå¸ĥä¼ļä¸Ĭ
    -0.08
    æ¦Ĥ
    -0.08
    anj
    -0.08
    POSITIVE LOGITS
    soever
    0.11
    ities
    0.10
    骧
    0.09
    æ¶Įçİ°
    0.09
    仪
    0.09
    讽åĪº
    0.09
    æѤæĸĩ
    0.09
    æĺĻ
    0.09
    主åŁİåĮº
    0.09
    绽
    0.09
    Activations Density 0.051%

    No Known Activations