© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15566
    Prev
    Next
    INDEX
    Explanations

    religious freedom and institutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    alysis
    -0.21
    ter
    -0.19
    ÑĩаÑĤ
    -0.18
    aceous
    -0.18
    ä¸ĢæµģçļĦ
    -0.17
    alytics
    -0.17
    trib
    -0.16
    autor
    -0.16
    oseconds
    -0.15
    ventions
    -0.15
    POSITIVE LOGITS
    ly
    0.32
    ness
    0.25
    LY
    0.23
    s
    0.23
    çĶ¨åĵģ
    0.21
    dom
    0.20
    ye
    0.20
    ×Ļ×Ŀ
    0.19
    dem
    0.18
    sing
    0.18
    Activations Density 0.004%

    No Known Activations