© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15086
    Prev
    Next
    INDEX
    Explanations

    roman numeral 4

    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
    qualities
    -0.20
    æĢĤ
    -0.20
    èĨĺ
    -0.19
    owitz
    -0.18
     chặt
    -0.18
    æ²½
    -0.18
    NavController
    -0.17
    çĵ¢
    -0.17
     оÑģобенно
    -0.17
    寡
    -0.17
    POSITIVE LOGITS
    _den
    0.21
    çĺ¾
    0.19
    /trunk
    0.19
     bump
    0.18
     Desc
    0.18
    æĭħå½ĵ
    0.18
    olib
    0.17
    tf
    0.17
    count
    0.17
     setInput
    0.17
    Activations Density 0.013%

    No Known Activations