© 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. 15661
    Prev
    Next
    INDEX
    Explanations

    sheer, lasts, film, chipping, or chromosome

    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
    碰
    -0.22
    æ¿Ĵ临
    -0.22
    Ã¤ÃŁ
    -0.21
     Sight
    -0.20
    æ¿Ĵ
    -0.20
    (Unknown
    -0.20
    åĭĩæķ¢
    -0.20
    SearchParams
    -0.19
    oola
    -0.19
    endas
    -0.19
    POSITIVE LOGITS
    åĪ°ä½į
    0.22
    åıłåĬł
    0.22
    層
    0.21
     layer
    0.20
    åĽº
    0.20
    Layer
    0.19
    åħ±è¯Ĩ
    0.19
     layers
    0.19
     повеÑĢÑħ
    0.19
    å±Ĥ次
    0.19
    Activations Density 0.004%

    No Known Activations