© 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. 13722
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

    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
    DetailsService
    -0.18
     Subscription
    -0.18
    ä½ı
    -0.16
    зÑĥ
    -0.16
    ATUS
    -0.16
    缮
    -0.16
    çĻ½
    -0.16
    éĢļ
    -0.16
    eln
    -0.16
    ç½®
    -0.16
    POSITIVE LOGITS
    åį¡çīĩ
    0.20
    箪
    0.20
    çĨĦ
    0.19
    çĤĴèĤ¡
    0.19
    è¾±
    0.19
    éĤ£ä¹Ī
    0.18
    ä½łæĢİä¹Ī
    0.18
    寡
    0.18
    è¹Ģ
    0.18
    åĮĸ身
    0.18
    Activations Density 0.048%

    No Known Activations