© 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. 39898
    Prev
    Next
    INDEX
    Explanations

    divine, gods, sacred concepts

    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
    ãģĦãĤĭ
    -0.09
     væ
    -0.09
    人们对
    -0.08
    æ°ijèIJ¥
    -0.08
    iness
    -0.08
     dür
    -0.08
    æĶ¿æĿĥ
    -0.08
    åĵĩ
    -0.08
    ä¼ļéĢłæĪIJ
    -0.08
    ä¸įä¿¡
    -0.08
    POSITIVE LOGITS
    -minded
    0.11
    ité
    0.11
    çĪ·
    0.11
    çĴĭ
    0.10
    ELY
    0.10
    ity
    0.10
    enco
    0.10
    ously
    0.10
    iture
    0.10
    -human
    0.09
    Activations Density 0.007%

    No Known Activations