© 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. 10877
    Prev
    Next
    INDEX
    Explanations

    damaged tissue

    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
    /or
    -0.24
    ìĿ´ê³ł
    -0.23
    建设åĴĮ
    -0.20
    à¹ģละ
    -0.20
     ÙĪØ®
    -0.20
    æķ²
    -0.19
    åĴĮ
    -0.19
    å¼Ģ车
    -0.18
    uc
    -0.17
    Callable
    -0.17
    POSITIVE LOGITS
    ç®Ģ称
    0.21
     Jah
    0.20
    ç»ĻæĪij们
    0.19
    å¼ķè¿Ľ
    0.18
    æ²ı
    0.18
    çģ¿
    0.17
     Lub
    0.17
    个人信æģ¯
    0.17
    coni
    0.17
    RODUCTION
    0.17
    Activations Density 0.275%

    No Known Activations