© 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. 15933
    Prev
    Next
    INDEX
    Explanations

    changing, degeneration, resize, bloom

    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
    pose
    -0.23
    tog
    -0.20
    ä»Ģä¹Īåij¢
    -0.20
    çļĦ人çĶŁ
    -0.19
    å°¼åħĭ
    -0.19
    æŃ¹
    -0.19
    æĺ¯éĿŀ
    -0.19
    éªŀ
    -0.19
    é£Ĵ
    -0.18
    æĨ¬
    -0.18
    POSITIVE LOGITS
     etc
    0.20
    rod
    0.20
    æijĩ
    0.19
     wang
    0.18
     iar
    0.18
    ogram
    0.18
    éļİ
    0.17
    æIJĸ
    0.17
    èĢĮ
    0.17
    ograms
    0.16
    Activations Density 0.280%

    No Known Activations