© 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. 15113
    Prev
    Next
    INDEX
    Explanations

    specific class names

    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
    ä¸įåľ¨
    -0.22
     Urg
    -0.18
    oundation
    -0.18
    åĢĴ
    -0.18
    Bind
    -0.17
    为空
    -0.17
    ·»
    -0.17
    è¾ľ
    -0.17
    iami
    -0.17
    basket
    -0.17
    POSITIVE LOGITS
    ifer
    0.19
    æĹ¥æĬ¥ç¤¾
    0.18
     ven
    0.18
    è¸ı
    0.18
     Ness
    0.17
    VES
    0.17
    广éĺĶ
    0.17
    踩
    0.17
    пл
    0.17
    æݨå¼Ģ
    0.17
    Activations Density 0.330%

    No Known Activations