© 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. 16734
    Prev
    Next
    INDEX
    Explanations

    customprivatecontactsuccessgeometricmediated

    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
    ä»įæľª
    -0.26
    å§Ķç»Ħç»ĩ
    -0.21
    è¿Ļåıª
    -0.20
    éĢļåijĬ
    -0.20
    startup
    -0.19
    |RF
    -0.19
    没èĥ½
    -0.18
    .proxy
    -0.18
     Startup
    -0.18
    æĻĥ
    -0.18
    POSITIVE LOGITS
    ä¸įåĥı
    0.34
     unlike
    0.31
     whereas
    0.26
    容æĺĵ
    0.26
     compared
    0.24
    ä¸įçĶ¨æĭħå¿ĥ
    0.23
     immedi
    0.21
     easily
    0.21
    ä¸įå¿ħ
    0.21
    æĥ¦
    0.21
    Activations Density 0.241%

    No Known Activations