© 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. 14750
    Prev
    Next
    INDEX
    Explanations

    keyboard and mouse

    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
    jun
    -0.22
     innoc
    -0.21
    .getvalue
    -0.20
    çݰ身
    -0.20
    .DataType
    -0.20
    çĽijåIJ¬é¡µéĿ¢
    -0.19
    .spinner
    -0.19
    ç¡ħè°·
    -0.19
     institutional
    -0.19
    usty
    -0.19
    POSITIVE LOGITS
    èĩªåĬ¨
    0.23
     action
    0.23
    æīĭåĬ¨
    0.22
    åij½ä»¤
    0.22
    åĬ¨ä½ľ
    0.22
    ãĤ¢ãĤ¯
    0.22
    æĵįæݧ
    0.22
     cá»Ń
    0.21
    ãĥ¼ãĥł
    0.21
    action
    0.21
    Activations Density 0.023%

    No Known Activations