© 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. 6674
    Prev
    Next
    INDEX
    Explanations

    AI

    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
    ings
    -0.09
    bos
    -0.09
    ãģ¾ãģĦ
    -0.09
    åĨĮ
    -0.09
    累累
    -0.08
    dam
    -0.08
    indre
    -0.08
    ego
    -0.08
    æľ¬äºº
    -0.08
    çĹĽçĤ¹
    -0.08
    POSITIVE LOGITS
    0.14
     Äijáo
    0.09
    owered
    0.09
    ạ
    0.08
    mega
    0.08
    å²Ĺ
    0.08
    黾
    0.08
    fully
    0.08
    ç´Ģ
    0.08
    avigate
    0.08
    Activations Density 0.031%

    No Known Activations