© 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. 15874
    Prev
    Next
    INDEX
    Explanations

    T-shirt or shirt

    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
    票
    -0.21
    essim
    -0.19
    ipple
    -0.19
    车载
    -0.19
    ä¸Ģ座
    -0.19
    ibi
    -0.18
    羣æĥħ
    -0.18
    æĺ¯ä¸Ģ座
    -0.18
     Rolls
    -0.18
    ance
    -0.18
    POSITIVE LOGITS
    è¡«
    0.29
    ãĥ¯ãĥ³
    0.23
    è¿Ļ件
    0.22
     shirt
    0.21
    èĥ¸åı£
    0.20
    丰满
    0.20
    æªĶ
    0.20
     shirts
    0.20
    ç«¥è£ħ
    0.20
    ðŁijķ
    0.19
    Activations Density 0.025%

    No Known Activations