© 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. 62310
    Prev
    Next
    INDEX
    Explanations

    sensor types

    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
    æĭĶ
    -0.10
    çıŃ车
    -0.10
    åķ¬
    -0.10
    æİ¥å¾ħ
    -0.10
    볨
    -0.10
    æ§İ
    -0.09
    åģıåIJij
    -0.09
    æ¹
    -0.09
    ниÑĩ
    -0.09
    æ±ĩ
    -0.09
    POSITIVE LOGITS
    ä¼łæĦŁåĻ¨
    0.16
     sensors
    0.13
    çĽijæµĭ
    0.13
     sensor
    0.12
    çĽijæݧ
    0.11
    ãĤ»ãĥ³
    0.11
     monitoring
    0.11
     Sensors
    0.11
    å¾®åŀĭ
    0.11
    çĽ£
    0.10
    Activations Density 0.253%

    No Known Activations