© 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. 14748
    Prev
    Next
    INDEX
    Explanations

    domains or activities

    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
     Noble
    -0.21
    éľĵ
    -0.20
    eldon
    -0.20
    ⣷
    -0.19
    踯
    -0.19
    utches
    -0.19
    èĪĶ
    -0.19
    unny
    -0.18
     Yapı
    -0.18
    onnen
    -0.18
    POSITIVE LOGITS
    æĪĸåħ¶ä»ĸ
    0.23
    常çĶ¨çļĦ
    0.23
    使çĶ¨çļĦ
    0.22
    çŃīè¡Įä¸ļ
    0.21
    ä¸ĵçĶ¨
    0.21
    常çĶ¨
    0.20
    æĪĸ
    0.20
    æīĢéľĢçļĦ
    0.19
    黡
    0.19
     or
    0.19
    Activations Density 1.172%

    No Known Activations