© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12328
    Prev
    Next
    INDEX
    Explanations

    develop a

    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
    cá
    -0.19
    çľī头
    -0.18
    éĹº
    -0.17
    à´®
    -0.17
    æĮ¥æīĭ
    -0.17
     sout
    -0.16
    ÑĩÑĮ
    -0.16
    -desc
    -0.16
    disposed
    -0.16
    âĨĺ
    -0.16
    POSITIVE LOGITS
    ä¸įåľ¨
    0.21
    ively
    0.20
    lyn
    0.19
     Eff
    0.19
    çķĻ
    0.18
    çķĻåľ¨
    0.18
    )\<
    0.17
    çıł
    0.17
    åł°
    0.17
    åĨħå¤ĸ
    0.16
    Activations Density 0.671%

    No Known Activations