© 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. 16144
    Prev
    Next
    INDEX
    Explanations

    absolutely safe and free

    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
    haps
    -0.25
    avin
    -0.20
    墨
    -0.19
    æĭĶ
    -0.19
    bast
    -0.19
    maybe
    -0.19
    éľ²
    -0.18
    åij½
    -0.18
     bast
    -0.18
     maybe
    -0.18
    POSITIVE LOGITS
    ç»Ŀ对ä¸įä¼ļ
    0.31
    ä¸įä¼ļ
    0.28
    ä¸įä¼ļæľī
    0.26
    ä¸įçĶ¨æĭħå¿ĥ
    0.25
    ä¹Łä¸įä¼ļ
    0.23
    ä¸Ŀ毫
    0.23
    ä¸įåŃĺåľ¨
    0.22
    ä¸įæľĥ
    0.22
    ä»»ä½ķ
    0.22
    ä¿Ŀè¯ģ
    0.21
    Activations Density 0.055%

    No Known Activations