© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15133
    Prev
    Next
    INDEX
    Explanations

    titles and specific names

    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
    çĤĬ
    -0.19
    å¥ij
    -0.19
     comp
    -0.19
    èѬå¦Ĥ
    -0.19
    ISK
    -0.18
    ORD
    -0.18
    inue
    -0.18
    GLOSS
    -0.18
    æĵį
    -0.18
    åľ¨æĪijçļĦ
    -0.18
    POSITIVE LOGITS
     Tüm
    0.21
    çľĦ
    0.20
    åİŁèijĹ
    0.19
    æĪ¿
    0.19
    ä½Ļ家
    0.19
    ä¼ļåIJĮ
    0.19
    æľ¬èº«å°±æĺ¯
    0.19
    umd
    0.19
    è´ŃæĪ¿
    0.18
    Ĭ¶
    0.18
    Activations Density 0.036%

    No Known Activations