© 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. 15826
    Prev
    Next
    INDEX
    Explanations

    What happens

    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
    arb
    -0.21
    lien
    -0.20
    hol
    -0.20
    t
    -0.19
    åħ¨å±Ģ
    -0.18
    åį³ä¾¿æĺ¯
    -0.18
    ä¾£
    -0.18
    astr
    -0.17
    emo
    -0.17
    aring
    -0.17
    POSITIVE LOGITS
    éĹ®ä»ĸ
    0.23
    为ä»Ģä¹Īä¼ļ
    0.21
    为ä½ķ
    0.21
    åıĹ访
    0.20
    é»Ŀ
    0.20
    çļĦåĽŀçŃĶ
    0.19
    æľĢåĸľæ¬¢
    0.19
    æľĢåĸľæ¬¢çļĦ
    0.19
    åħ¶å®ĥéĹ®é¢ĺ
    0.19
    ä½łè§īå¾Ĺ
    0.19
    Activations Density 0.009%

    No Known Activations