© 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. 16393
    Prev
    Next
    INDEX
    Explanations

    last names

    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
     substring
    -0.18
     Old
    -0.17
    idual
    -0.17
     lã
    -0.17
    \Template
    -0.17
    Substring
    -0.17
    ä¹Łç®Ĺ
    -0.17
    骰
    -0.17
    æ·¦
    -0.17
     glyphicon
    -0.17
    POSITIVE LOGITS
    å¼Ń
    0.20
    à¸Ńำà¸Ļวยà¸Ħวาม
    0.19
    åı£æ°Ķ
    0.19
    æķijæĬ¤è½¦
    0.19
    ç¿Ģ
    0.19
    sher
    0.19
    å¹²é¢Ħ
    0.19
    仲
    0.19
    çłĶ究æīĢ
    0.18
    åij½
    0.18
    Activations Density 0.001%

    No Known Activations