© 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. 11261
    Prev
    Next
    INDEX
    Explanations

    marketing and strategy planning

    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
    otland
    -0.24
     Downs
    -0.22
    çݰ代社ä¼ļ
    -0.22
    æ°ijä¼Ĺ
    -0.22
     Fellowship
    -0.21
    çĶŁäº§çĶŁæ´»
    -0.21
    åįĥå¹´
    -0.20
    Repair
    -0.20
    å¿ĹæĦ¿èĢħ
    -0.20
    RAL
    -0.20
    POSITIVE LOGITS
    çŃĸçķ¥
    0.29
    çĽ¯
    0.28
    çĽijæݧ
    0.26
    èĮĥåĨ°
    0.26
    æĪĺçķ¥
    0.26
    ä¸Ĭ线
    0.25
    á¿ij
    0.25
     Geile
    0.25
    è¶ĭåĬ¿
    0.25
     Prostitutas
    0.24
    Activations Density 0.116%

    No Known Activations