© 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. 13517
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     komm
    -0.21
    å®ĺ
    -0.20
     Pars
    -0.19
    룩
    -0.18
    æĤ¦
    -0.18
    å·½
    -0.18
    å°Ĭæķ¬
    -0.18
    å®ĺæĸ¹
    -0.18
    åij½åIJį
    -0.18
     Likes
    -0.18
    POSITIVE LOGITS
    PTION
    0.20
    ä¸ī大
    0.19
    unlink
    0.19
    çĽ¸å·®
    0.18
    -collar
    0.17
    boro
    0.17
    窦
    0.17
    ãģĵ
    0.17
    åŀŃ
    0.17
     colspan
    0.17
    Activations Density 0.000%

    No Known Activations