© 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. 16738
    Prev
    Next
    INDEX
    Explanations

    National Route

    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¿Ŀå§Ĩ
    -0.22
    婶
    -0.21
    ä¸İåħ¶
    -0.19
    èĭ
    -0.19
    éĺ¿å§¨
    -0.18
    atism
    -0.18
    æĪ·åı£
    -0.18
     zoom
    -0.18
    çĶ¨å·¥
    -0.17
     пÑĢоиÑģ
    -0.17
    POSITIVE LOGITS
    hidden
    0.21
    ä¿¡ç®±
    0.21
     mail
    0.21
    mail
    0.20
    .mail
    0.20
    è¢ľ
    0.19
    rece
    0.18
     Generator
    0.18
     mails
    0.18
    åŀĥåľ¾
    0.18
    Activations Density 0.006%

    No Known Activations