© 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. 14299
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and company names

    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
    大åĬĽ
    -0.23
    ynos
    -0.21
     maturity
    -0.20
    çģ«çĥŃ
    -0.18
    åĪ¶åº¦
    -0.18
    åį¡
    -0.18
    ä¸Ģä½ĵ
    -0.17
    íĺĪ
    -0.17
     ACK
    -0.17
     chÃŃ
    -0.17
    POSITIVE LOGITS
    è°®
    0.21
    izzo
    0.19
    Children
    0.19
    èĻIJ
    0.19
    就说
    0.19
     Children
    0.19
    对åŃ©åŃIJ
    0.19
    åŃ©åŃIJ们
    0.19
    æķĻæİĪ
    0.18
    æŁĶ
    0.18
    Activations Density 0.003%

    No Known Activations