© 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. 37108
    Prev
    Next
    INDEX
    Explanations

    separate, separation

    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
    å±ı
    -0.10
    èĨ³
    -0.09
    å´Ľ
    -0.09
    ENDING
    -0.09
    æ¯Ĥ
    -0.09
    à¹Ĥ
    -0.09
    磫
    -0.09
     thả
    -0.09
    EventType
    -0.08
    墩
    -0.08
    POSITIVE LOGITS
    åĪĨå¼Ģ
    0.14
    æĭŃ
    0.12
    åĪĨ离
    0.12
     оÑĤдел
    0.10
    çĤĻ
    0.10
     separ
    0.10
     Separ
    0.10
     separation
    0.10
    åĴ«
    0.10
    æĢĿ
    0.09
    Activations Density 0.075%

    No Known Activations