© 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. 19084
    Prev
    Next
    INDEX
    Explanations

    god and related religious terms

    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
    ÑģÑı
    -0.10
    ingly
    -0.10
    erset
    -0.09
    ilion
    -0.09
     dra
    -0.09
    æĶ¿æĿĥ
    -0.09
    illard
    -0.09
    ĺ认
    -0.08
    itag
    -0.08
     unint
    -0.08
    POSITIVE LOGITS
    damn
    0.11
    frey
    0.10
    åºĻ
    0.10
    å»Ł
    0.09
    zilla
    0.09
    ç¥ĩ
    0.09
    åĢij
    0.09
    ãĤį
    0.09
    ray
    0.09
    çĦ¶æĺ¯
    0.09
    Activations Density 0.025%

    No Known Activations