© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20936
    Prev
    Next
    INDEX
    Explanations

    below ground

    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
    åĵĦ
    -0.09
    éºĭ
    -0.08
    shan
    -0.08
    éªĹåıĸ
    -0.08
    è¥Ł
    -0.08
    _LOOK
    -0.08
    ToPoint
    -0.08
    æijĨåľ¨
    -0.08
     lac
    -0.08
    IRON
    -0.08
    POSITIVE LOGITS
    åľ°ä¸ĭ
    0.23
     underground
    0.18
    åŁĭ
    0.18
     Underground
    0.15
     depths
    0.13
     beneath
    0.13
    èĽ°
    0.13
    åľ°ä¸ĭæ°´
    0.13
    深度
    0.13
    åľ°ä¸ĭ室
    0.13
    Activations Density 0.221%

    No Known Activations