© 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. 18834
    Prev
    Next
    INDEX
    Explanations

    composers and musical works

    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
    .literal
    -0.09
    åIJĦè¡Į
    -0.09
    ÑĢин
    -0.09
    ÑĪив
    -0.09
    .lin
    -0.09
    å¹³æŶ
    -0.09
    æ¯ıä¸Ģ天
    -0.09
    bable
    -0.09
     Bloomberg
    -0.08
    .Arguments
    -0.08
    POSITIVE LOGITS
    è¥Ł
    0.09
    hay
    0.09
    è¯ŀ
    0.08
    ç»ıåħ¸
    0.08
    ëĬĶëį°
    0.08
    ever
    0.08
    åĪ¶è®¢
    0.08
    SEP
    0.08
    umn
    0.08
    ique
    0.08
    Activations Density 0.026%

    No Known Activations