© 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. 14683
    Prev
    Next
    INDEX
    Explanations

    vacation rentals or home booking

    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
    igner
    -0.17
    hole
    -0.16
    ritten
    -0.16
    ached
    -0.16
     Grat
    -0.15
    ams
    -0.15
    âģ¾
    -0.15
    ãģ£ãģ¨
    -0.15
    ÑģÑĤо
    -0.15
     ÑģебÑı
    -0.15
    POSITIVE LOGITS
    ary
    0.21
    ally
    0.19
    ous
    0.19
    ا
    0.18
    ation
    0.18
    -ending
    0.18
    åħ®
    0.17
    ²
    0.17
    matic
    0.17
    er
    0.17
    Activations Density 0.012%

    No Known Activations