© 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. 17619
    Prev
    Next
    INDEX
    Explanations

    musical instrument names

    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
    èģĶæĥ³
    -0.11
    è·Łä¸įä¸Ĭ
    -0.10
    ç§¦åĽ½
    -0.10
    天æĸĩ
    -0.09
    æĦī
    -0.09
    orte
    -0.09
    æIJĸ
    -0.09
    çĶ»çĶ»
    -0.09
    sole
    -0.09
    omics
    -0.09
    POSITIVE LOGITS
    对åѦçĶŁ
    0.09
    èĻĽ
    0.08
    转åIJij
    0.08
    à¹ģà¸ģ
    0.08
    ç»ĪçĶŁ
    0.08
     Vox
    0.07
    æķĻèĤ²æķĻåѦ
    0.07
    示èĮĥ
    0.07
    èĻļ
    0.07
    msp
    0.07
    Activations Density 0.048%

    No Known Activations