© 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. 17352
    Prev
    Next
    INDEX
    Explanations

    personal reaction with "me"

    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
    ä¸Ĭåİ»
    -0.10
    æĪijå¿ĥéĩĮ
    -0.10
    NESS
    -0.10
    å±ģèĤ¡
    -0.09
    墩
    -0.09
    çĦī
    -0.09
    ABLE
    -0.09
    èģĶç³»çĶµè¯Ŀ
    -0.09
    izzard
    -0.08
    ä¸ĭåİ»
    -0.08
    POSITIVE LOGITS
     лиÑĩно
    0.10
    æīī
    0.09
    ç¨ĭ度
    0.09
    è¿ĻéĩĮæĺ¯
    0.09
    ingly
    0.09
    æīĢåľ¨
    0.09
    å¿ĥæĻº
    0.08
    è¿Ļ座
    0.08
    ä¸įå·²
    0.08
    itel
    0.08
    Activations Density 0.030%

    No Known Activations