© 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. 58511
    Prev
    Next
    INDEX
    Explanations

    recognize familiar recognition

    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
    访
    -0.11
    ettel
    -0.10
    æĬ¹
    -0.10
     rum
    -0.09
    èľĥ
    -0.09
    åľŃ
    -0.09
    å¼ŁåħĦ
    -0.09
    èĮ¶
    -0.09
    _accessible
    -0.09
    èĢĮåİ»
    -0.09
    POSITIVE LOGITS
    è¯ĨåĪ«
    0.12
     recognizable
    0.10
    认
    0.10
     recognition
    0.10
    Recognition
    0.10
    辨
    0.10
     Recogn
    0.09
     recognize
    0.09
    recogn
    0.09
     Recognition
    0.09
    Activations Density 0.055%

    No Known Activations