© 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. 16140
    Prev
    Next
    INDEX
    Explanations

    hopefully

    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
    زاÙĦ
    -0.23
    åºķ
    -0.21
     доÑģÑĤ
    -0.20
    åī¯
    -0.18
     Anth
    -0.18
    è¿Ļæĺ¯åĽłä¸º
    -0.18
    å¢ĥå¤ĸ
    -0.18
    ØŃÙĨ
    -0.18
    纹
    -0.17
    ä¸Ģå¾ĭ
    -0.17
    POSITIVE LOGITS
    æĪijçĽ¸ä¿¡
    0.25
    以ä¸ĬçļĦ
    0.24
     hopefully
    0.24
    以ä¸Ĭ
    0.22
    çĽ¸ä¿¡å¤§å®¶
    0.21
    åı¯ä»¥çľĭåĩº
    0.21
    hopefully
    0.21
    亲çĪ±çļĦ
    0.21
    ãģĵãģĵãģ¾ãģ§
    0.20
    Hopefully
    0.19
    Activations Density 0.016%

    No Known Activations