© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51350
    Prev
    Next
    INDEX
    Explanations

    competition outcomes

    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
    iry
    -0.11
    常年
    -0.10
    æµģæ·Į
    -0.09
    æĪĹ
    -0.09
    ä¸Ģå¦Ĥ
    -0.09
    ä½ļ
    -0.09
    ÑĢен
    -0.09
    éĢIJå¹´
    -0.09
    riba
    -0.09
    æĹħ游å±Ģ
    -0.09
    POSITIVE LOGITS
    ä¸įä¹ħåīį
    0.12
    åīįä¸įä¹ħ
    0.10
    ä¸Ĭ次
    0.10
    ä¸Ĭåij¨
    0.09
     yesterday
    0.09
     recently
    0.09
    尤为
    0.09
     hôm
    0.09
    æĺ¨å¤©
    0.09
    Spoiler
    0.08
    Activations Density 0.037%

    No Known Activations