© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53037
    Prev
    Next
    INDEX
    Explanations

    digital commons

    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
    lash
    -0.09
    ÐŀÐĿ
    -0.09
     Hur
    -0.08
    æĸĩ娱
    -0.08
    åŃ£åº¦
    -0.08
    æĭ¯
    -0.08
    ãģµ
    -0.08
     дол
    -0.08
    æºħ
    -0.08
    å¤įå·¥å¤į产
    -0.08
    POSITIVE LOGITS
    deposit
    0.10
    iolet
    0.09
    棱
    0.09
    edic
    0.09
    ä¸Ĭä¼ł
    0.09
    _collections
    0.09
     Stamina
    0.09
     deposit
    0.09
    åĽ½æľīèµĦ产
    0.09
    edral
    0.08
    Activations Density 0.041%

    No Known Activations