© 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. 15813
    Prev
    Next
    INDEX
    Explanations

    broken link, broken into, broken for

    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
    è¿Ļæł·è¯´
    -0.21
    è´¯
    -0.20
    è¿Ļä¹Ī说
    -0.20
    arus
    -0.20
    emaker
    -0.20
    æĭīæĸ¯
    -0.18
    ilage
    -0.18
    ittal
    -0.18
    羯
    -0.18
    .hstack
    -0.18
    POSITIVE LOGITS
    AMI
    0.19
    åļ£
    0.19
     fmt
    0.19
    fmt
    0.18
    outh
    0.18
    åºĶçĶ¨
    0.18
    èĪĴéĢĤ
    0.18
    åŁ
    0.18
     dope
    0.18
     ld
    0.17
    Activations Density 0.015%

    No Known Activations