© 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. 13641
    Prev
    Next
    INDEX
    Explanations

    sociology

    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
    åħħ足
    -0.18
     Svens
    -0.18
    icter
    -0.18
     лиÑĪÑĮ
    -0.17
    mtree
    -0.17
    chner
    -0.17
    ä¸ĢåĽŀäºĭ
    -0.17
    tör
    -0.17
    bsite
    -0.17
    çijľ
    -0.16
    POSITIVE LOGITS
    ems
    0.20
    -minded
    0.19
    /social
    0.18
    uration
    0.18
    -economic
    0.18
    ä¸ĩ象
    0.18
    upt
    0.17
    ologies
    0.17
    ements
    0.17
    éĺ¶å±Ĥ
    0.17
    Activations Density 0.010%

    No Known Activations