© 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. 62011
    Prev
    Next
    INDEX
    Explanations

    english language and literature

    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
    uron
    -0.09
    æĭĨè¿ģ
    -0.08
    ç¼´è´¹
    -0.08
    éĽªèĬ±
    -0.08
    át
    -0.08
    Formats
    -0.08
    åı¯æł¹æį®
    -0.08
     gaz
    -0.08
    _echo
    -0.08
    åij¼åºĶ
    -0.08
    POSITIVE LOGITS
    èĭ±è¯Ń
    0.19
     English
    0.18
     english
    0.18
     англий
    0.16
    English
    0.16
    english
    0.15
    å¤ĸè¯Ń
    0.15
    è¯Ńè¨Ģ
    0.15
     language
    0.14
    -language
    0.13
    Activations Density 0.103%

    No Known Activations