© 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. 16467
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    (~
    -0.20
    æı
    -0.20
     gaz
    -0.20
    See
    -0.20
    mo
    -0.20
    Cre
    -0.19
     roughly
    -0.19
    agar
    -0.19
     vast
    -0.19
    ener
    -0.19
    POSITIVE LOGITS
    ä¸įæħİ
    0.26
    æģ°å¥½
    0.25
    éĹ®
    0.25
    èĥ½ä½¿
    0.25
    å¿ĺäºĨ
    0.22
    _tE
    0.22
    éľĢè¦ģçĶ¨
    0.21
     нÑĥжно
    0.21
    findViewById
    0.20
    -find
    0.20
    Activations Density 0.708%

    No Known Activations