© 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. 10989
    Prev
    Next
    INDEX
    Explanations

    earning a living or livelihood

    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
    æĦıå¢ĥ
    -0.20
    ãģĤãģ£ãģŁ
    -0.17
    èĻļæŀĦ
    -0.17
    æĢĿç»´
    -0.16
    é«ĺå±Ĥ
    -0.16
    InputModule
    -0.16
    åĩºæĿ¥çļĦ
    -0.16
     cons
    -0.15
    们çļĦ
    -0.15
    æĦı
    -0.15
    POSITIVE LOGITS
    -threatening
    0.22
     livelihood
    0.20
    涯
    0.20
    еÑģÑĮ
    0.19
    iest
    0.19
    arily
    0.19
    acket
    0.18
    ÑĮ
    0.17
    aupt
    0.17
    THING
    0.17
    Activations Density 0.003%

    No Known Activations