© 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. 5184
    Prev
    Next
    INDEX
    Explanations

    catch or conditions

    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
    UniqueId
    -0.09
    åĶ±
    -0.09
    笼
    -0.09
    ãģĮãģ§ãģį
    -0.08
    аÑĢаÑĤ
    -0.08
    èĤ²
    -0.08
    æ°´åĩĨ
    -0.08
    赤
    -0.08
    uve
    -0.08
    家ä¸Ń
    -0.08
    POSITIVE LOGITS
    æĿ¡ä»¶
    0.18
    æ¢Ŀ件
    0.17
    éĻIJåĪ¶
    0.17
    éĻIJå®ļ
    0.16
    éĻIJéĩı
    0.16
     conditions
    0.16
    conditions
    0.15
    Conditions
    0.15
     Conditions
    0.14
     ÑĥÑģлов
    0.14
    Activations Density 0.096%

    No Known Activations