© 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. 16060
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    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
     ÐIJлекÑģан
    -0.33
     ÐŁÐ¾Ñĩем
    -0.32
     поÑģколÑĮ
    -0.28
     PaÅĦstwo
    -0.26
     ÐĶмиÑĤÑĢ
    -0.26
     подÑĢобн
    -0.24
     пÑĢиÑıÑĤн
    -0.24
    ÑĩÑĢежден
    -0.22
     заÑĢегиÑģÑĤ
    -0.22
     ÑĦоÑĢмиÑĢова
    -0.21
    POSITIVE LOGITS
    -
    0.26
    ÑģÑĥд
    0.20
    Âł
    0.19
    ·
    0.19
    Å°
    0.18
    /
    0.18
    âĨ½
    0.18
    hợ
    0.18
    0.18
     "
    0.17
    Activations Density 0.051%

    No Known Activations