© 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. 14552
    Prev
    Next
    INDEX
    Explanations

    tag or label

    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
    æĹħéĢĶ
    -0.19
    oured
    -0.19
     Illustrated
    -0.18
    éħĬ
    -0.18
    æºIJæ³ī
    -0.17
    èĢģ年人
    -0.17
    åģ¥åº·ç®¡çIJĨ
    -0.17
    igated
    -0.16
    çŀ»
    -0.16
    utch
    -0.16
    POSITIVE LOGITS
    ä¸Ģå¼ł
    0.25
     attached
    0.25
    ä¸ĬçļĦ
    0.24
    less
    0.22
    attached
    0.22
     fresh
    0.21
    ä¸Ģ份
    0.20
    ä¸Ģæµģ
    0.20
    æİı
    0.19
    ä¸Ĭæľī
    0.19
    Activations Density 0.006%

    No Known Activations