© 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. 56466
    Prev
    Next
    INDEX
    Explanations

    life cycle definitive host

    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
    é¹Ĺ
    -0.10
    ä¼ı
    -0.09
    åŃķ
    -0.09
    åħĶ
    -0.09
    çĸı
    -0.09
    xfb
    -0.09
    благо
    -0.09
    çķĽ
    -0.09
    ÑĢеги
    -0.09
    è¹Ģ
    -0.08
    POSITIVE LOGITS
     Cycle
    0.10
     tal
    0.09
     cycle
    0.09
    ä¼łå¥ĩ
    0.09
    èĸª
    0.09
    èĵ¼
    0.09
    ä¼łæĴŃ
    0.09
    _cycle
    0.09
     modes
    0.08
     ÑħозÑı
    0.08
    Activations Density 0.158%

    No Known Activations