© 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. 13237
    Prev
    Next
    INDEX
    Explanations

    pizza and pie

    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
    åģļä¸Ģ个
    -0.19
    åĤ·
    -0.18
    tle
    -0.18
    æĥļ
    -0.18
    upp
    -0.17
     slate
    -0.17
    ä¸Ńèį¯æĿIJ
    -0.17
    å¦Ĩ
    -0.17
    arf
    -0.17
    ÑıÑģн
    -0.17
    POSITIVE LOGITS
     pizza
    0.24
     Pizza
    0.20
    htm
    0.19
    ðŁįķ
    0.19
    hook
    0.18
    ТÐĺ
    0.18
    æķ°é¢Ŀ
    0.18
    ongan
    0.18
    pizza
    0.18
    arium
    0.17
    Activations Density 0.002%

    No Known Activations