© 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. 9403
    Prev
    Next
    INDEX
    Explanations

    degree available considerable detail

    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
    strup
    -0.10
    çļĤ
    -0.10
    aised
    -0.09
     dú
    -0.09
    onis
    -0.09
    óc
    -0.09
    amation
    -0.09
    auty
    -0.09
    çħĮ
    -0.09
    .ov
    -0.09
    POSITIVE LOGITS
    人们对
    0.10
    éĦ¢
    0.09
    åIJĦç§į
    0.09
    åĽĽä¸ª
    0.09
    被人
    0.09
    éĤ£ç§į
    0.09
    ä¸Ģ个éĹ®é¢ĺ
    0.08
    ä¸Ģæī¹
    0.08
    ä¸įä¸Ģæł·çļĦ
    0.08
    ä»Ģä¹Īäºĭæĥħ
    0.08
    Activations Density 0.177%

    No Known Activations