© 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. 15666
    Prev
    Next
    INDEX
    Explanations

    showing results or explanations

    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
    udit
    -0.17
    ities
    -0.16
    çļĦèĦļæŃ¥
    -0.16
    表述
    -0.16
    -0.16
    qu
    -0.16
     thoại
    -0.15
    amer
    -0.15
    wine
    -0.15
    媳
    -0.15
    POSITIVE LOGITS
    manship
    0.24
    ings
    0.24
    ä¸įåĩºæĿ¥
    0.23
    cased
    0.20
    biz
    0.20
     casing
    0.19
     ÑģебÑı
    0.18
    æĻ°
    0.18
    äºĽä»Ģä¹Ī
    0.17
    atics
    0.17
    Activations Density 0.102%

    No Known Activations