© 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. 16018
    Prev
    Next
    INDEX
    Explanations

    due to reasons

    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¸Ģä½ĵ
    -0.25
    å¨ĵ
    -0.20
     strugg
    -0.20
    享åıĹåĪ°
    -0.20
    /ay
    -0.20
    utral
    -0.20
    çļĦçĪ±æĥħ
    -0.20
    å¾Īå¼Ģå¿ĥ
    -0.20
    ä½ĵä¼ļåĪ°
    -0.20
    è¿Ļæīįæĺ¯
    -0.19
    POSITIVE LOGITS
     lack
    0.22
    Either
    0.20
    due
    0.20
     too
    0.20
    ç§įç§į
    0.20
    åİŁåĽłæĺ¯
    0.20
    lx
    0.19
    ä¼ģåĽ¾
    0.19
     due
    0.19
    ish
    0.18
    Activations Density 0.120%

    No Known Activations