© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51684
    Prev
    Next
    INDEX
    Explanations

    parts or volumes with numbers

    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
    为主çļĦ
    -0.08
     Martins
    -0.08
    gere
    -0.08
     EGL
    -0.08
    smith
    -0.08
     Coal
    -0.08
    ç¾
    -0.08
    adin
    -0.08
    ä¸Ģ线
    -0.08
    íĺ¼
    -0.08
    POSITIVE LOGITS
    ä¸ĢæľŁ
    0.11
    误解
    0.10
     edition
    0.09
    çĶŁæľº
    0.09
    è¾ij
    0.09
    修订
    0.09
    äºĮæľŁ
    0.09
    çĤ¹æ»´
    0.09
    éļħ
    0.09
    误ä¼ļ
    0.09
    Activations Density 0.175%

    No Known Activations