© 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. 13745
    Prev
    Next
    INDEX
    Explanations

    rounding to decimal places or steps

    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
    æ±
    -0.19
    ä¾Ŀæ³ķ
    -0.18
    è¶ħ
    -0.18
    ème
    -0.18
    ç«Ļåľ¨
    -0.18
    .effects
    -0.18
    íĥģ
    -0.17
    bern
    -0.17
     Residents
    -0.17
    burger
    -0.17
    POSITIVE LOGITS
     precision
    0.29
    Precision
    0.27
    精度
    0.26
    精确
    0.26
     accuracy
    0.26
     Precision
    0.25
    ç²¾åĩĨ
    0.24
    è¹¼
    0.24
     increments
    0.23
    accuracy
    0.22
    Activations Density 0.064%

    No Known Activations