© 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. 11225
    Prev
    Next
    INDEX
    Explanations

    chocolate bar

    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
    ÑģÑĤи
    -0.21
    forth
    -0.20
    ÄŃ
    -0.19
    çŃļ
    -0.18
    elin
    -0.18
    湫
    -0.18
    ipur
    -0.17
    arde
    -0.17
    åĩ¡
    -0.17
    itorio
    -0.17
    POSITIVE LOGITS
    caffe
    0.20
    æĿ¯
    0.18
    æݨèįIJéĺħ读
    0.17
    keys
    0.17
    çĦĻ
    0.17
    åĴĸåķ¡
    0.17
    apple
    0.17
    éĻ¢éĻ¢éķ¿
    0.17
    phant
    0.16
    åĪĨãģĭãĤĭ
    0.16
    Activations Density 0.006%

    No Known Activations