© 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. 16337
    Prev
    Next
    INDEX
    Explanations

    don't ask

    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
    æĦıæĥ³ä¸įåĪ°
    -0.21
     caÅĤ
    -0.20
    并ä¸įæĺ¯
    -0.19
     ganz
    -0.19
    没èĥ½
    -0.18
    èĢĮä¸įæĺ¯
    -0.18
    ANGLE
    -0.18
    ä¸įåħĭä¸įåıĬ
    -0.18
     perse
    -0.18
    CLE
    -0.18
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.29
     anything
    0.25
    ä»»ä½ķå½¢å¼ı
    0.25
    ä»»ä½ķ
    0.22
     anymore
    0.22
    åħ·ä½ĵåĨħ容
    0.21
    太ä¹ħ
    0.21
    ä»»ä½ķ人
    0.20
     Anything
    0.20
    éĤ£ç§į
    0.20
    Activations Density 0.029%

    No Known Activations