© 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. 16559
    Prev
    Next
    INDEX
    Explanations

    waves

    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
     DeV
    -0.20
    -piece
    -0.20
    .prevent
    -0.20
    (strategy
    -0.19
     Twilight
    -0.19
    .failure
    -0.19
     accelerated
    -0.19
    azzi
    -0.19
    .accel
    -0.19
    osen
    -0.18
    POSITIVE LOGITS
    å½±åĵįåĬĽçļĦ
    0.21
    éĽ·è¾¾
    0.21
    åĪ¶è£ģ
    0.21
    çIJĨæĥ³
    0.20
    主导
    0.20
    è¿ĩå¾Ģ
    0.20
    çĽ¸å¹²
    0.20
    å¤ĸæ±ĩ
    0.19
    æľ¬åij¨
    0.19
    é¢ĦæĬ¥
    0.19
    Activations Density 0.003%

    No Known Activations