© 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. 12110
    Prev
    Next
    INDEX
    Explanations

    performance and appearances

    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
    _exempt
    -0.21
    .gg
    -0.21
    å¸Ĥåľºç«ŀäºī
    -0.21
    对å¤ĸ
    -0.20
    åij±
    -0.20
    åĬŀçIJĨ
    -0.19
    itives
    -0.18
    Detailed
    -0.18
     rÃłng
    -0.18
    ease
    -0.18
    POSITIVE LOGITS
    è´¡çĮ®
    0.22
    è¿ŀ线
    0.21
    第ä¸Ģ书记
    0.21
    èĥ¶åĽĬ
    0.20
    åIJĪä½ľ
    0.20
     surprise
    0.20
    çĤ¹çĩĥ
    0.20
    åĩ¤åĩ°
    0.20
     controversial
    0.19
    æľ¬å±Ĭ
    0.19
    Activations Density 0.034%

    No Known Activations