© 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. 17069
    Prev
    Next
    INDEX
    Explanations

    Host Bus Adapter

    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
    кова
    -0.09
    лей
    -0.08
    è¿Ļç§į
    -0.08
    --------------------------------------------------------------------------↵
    -0.08
    пÑĥ
    -0.08
    пи
    -0.08
     Vatican
    -0.07
     اÙĦجÙĩ
    -0.07
    еÑĩен
    -0.07
    ucc
    -0.07
    POSITIVE LOGITS
    ä¸Ģ件äºĭ
    0.11
    æļ¨
    0.11
    å·
    0.11
    以ä¸ĭç®Ģ称
    0.09
    å¨ģåIJį
    0.09
    å·ħå³°
    0.09
    åļĨ
    0.08
    æµ·è¿IJ
    0.08
    ä½Ĩæĺ¯ä»ĸ
    0.08
    ä¸ļä½Ļ
    0.08
    Activations Density 2.022%

    No Known Activations