© 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. 13612
    Prev
    Next
    INDEX
    Explanations

    package management commands

    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
    epy
    -0.25
    HW
    -0.20
    éĴī
    -0.19
    ç¡®å®ŀæĺ¯
    -0.19
    åıªä¸º
    -0.19
    è°Ģ
    -0.17
    ä»ĸè¿ĺ
    -0.17
    'R
    -0.17
    äºĭä¸ļ
    -0.17
    åħ¶ä»ĸ
    -0.17
    POSITIVE LOGITS
     similarly
    0.20
     likewise
    0.20
    odef
    0.19
     recip
    0.18
    èĭ¥å¹²
    0.18
     Likewise
    0.18
     ÑĤоже
    0.18
    çľĭä½ł
    0.18
    à¸ķรา
    0.17
    itsu
    0.17
    Activations Density 0.158%

    No Known Activations