© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17071
    Prev
    Next
    INDEX
    Explanations

    money amounts and costs

    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
    Negative Logits
     ÐIJлекÑģан
    -0.25
    åIJĮæł·
    -0.19
     ÐŁÐ¾Ñĩем
    -0.19
     ÐĶмиÑĤÑĢ
    -0.18
    è¤Ĭ
    -0.18
     Müd
    -0.18
    kÅĤad
    -0.17
     моÑīн
    -0.17
     ÑĢÑĥков
    -0.17
    usal
    -0.17
    POSITIVE LOGITS
     XXX
    0.17
    âĢ
    0.17
    0.17
    Âł
    0.17
     Skate
    0.17
    ï¸
    0.17
     æĸ¹
    0.17
    çĹķ
    0.16
    .jupiter
    0.16
     xxx
    0.16
    Activations Density 0.083%

    No Known Activations