© 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. 16083
    Prev
    Next
    INDEX
    Explanations

    settings and options

    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
    人éĹ´
    -0.24
    /apis
    -0.21
     verk
    -0.21
    /he
    -0.21
    /gallery
    -0.20
    åµĺ
    -0.19
    iaux
    -0.19
    詹å§Ĩæĸ¯
    -0.19
    ataire
    -0.19
    اÙĨÙĬØ©
    -0.19
    POSITIVE LOGITS
    æݧåĪ¶
    0.38
     settings
    0.34
     control
    0.33
    è°ĥæķ´
    0.32
    è°ĥèĬĤ
    0.32
     æݧ
    0.30
     options
    0.29
     controls
    0.28
    éĢī项
    0.28
    æݧ
    0.27
    Activations Density 0.281%

    No Known Activations