© 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. 7336
    Prev
    Next
    INDEX
    Explanations

    religious or spiritual 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
    SCRIBE
    -0.10
    linger
    -0.10
    ä½Ī
    -0.10
    licence
    -0.09
    æ²½
    -0.09
    åѤ
    -0.09
    çļĦéĴ±
    -0.09
    napshot
    -0.09
    éĤ£æł·çļĦ
    -0.09
    OwnProperty
    -0.08
    POSITIVE LOGITS
    绣ä¸Ģ
    0.10
    åĸľ
    0.10
    顶
    0.09
    éĻĭ
    0.09
    æ²Ļåıijä¸Ĭ
    0.09
    æł¸å¿ĥåĮº
    0.09
    çIJĽ
    0.08
     riv
    0.08
    ume
    0.08
    TextLabel
    0.08
    Activations Density 0.171%

    No Known Activations