© 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. 49899
    Prev
    Next
    INDEX
    Explanations

    high-profile events and statuses

    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
    åĩĨ
    -0.10
    ç»Ŀ对
    -0.09
    主æĦı
    -0.08
    pression
    -0.08
    èѦæĥķ
    -0.08
    ç¾İ好çĶŁæ´»
    -0.08
    çłļ
    -0.08
     плоÑĤ
    -0.08
    Props
    -0.08
     absolute
    -0.08
    POSITIVE LOGITS
    /high
    0.12
    /private
    0.10
    ãģª
    0.10
    _UNSIGNED
    0.10
    çľĭçĤ¹
    0.10
     enough
    0.09
    _GRA
    0.09
    æ²Ļ
    0.08
    ç¿Ł
    0.08
    AKER
    0.08
    Activations Density 0.003%

    No Known Activations