© 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. 14797
    Prev
    Next
    INDEX
    Explanations

    divine mission or weapon

    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
    udio
    -0.18
    ðŁı»
    -0.18
    ÙĨ
    -0.18
    è¿Ļ个ä¸ĸçķĮ
    -0.16
    imes
    -0.16
    ãģĦãĤĭ
    -0.16
    rema
    -0.16
    quette
    -0.15
    ÙĨÙĪ
    -0.15
    ÙĪد
    -0.15
    POSITIVE LOGITS
    -minded
    0.22
    ity
    0.21
    idad
    0.19
    -looking
    0.19
    -human
    0.18
    iture
    0.18
    ITY
    0.18
    ities
    0.17
    踪
    0.17
     обÑĢазом
    0.17
    Activations Density 0.014%

    No Known Activations