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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10876
    Prev
    Next
    INDEX
    Explanations

    legal action or lawsuits

    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
    æĬĺ
    -0.08
    åīģ
    -0.08
    åĨ¬å¤©
    -0.08
    æħ·æħ¨
    -0.08
    å¿ĥè¡Ģ
    -0.08
    åĽļ
    -0.08
    å¼¹
    -0.08
     variant
    -0.08
    举è¡ĮäºĨ
    -0.08
    åĪ½
    -0.08
    POSITIVE LOGITS
    ahn
    0.09
    寻æ±Ĥ
    0.09
    ÙģÙĨ
    0.09
    æıIJèµ·
    0.08
    assis
    0.08
     dawn
    0.08
    èļĮ
    0.08
    ниÑĨа
    0.08
    Naming
    0.08
    èģĺ请
    0.08
    Activations Density 0.188%

    No Known Activations