© 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. 14110
    Prev
    Next
    INDEX
    Explanations

    social media, pages, profiles, networks

    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
    ç»ıæµİæįŁå¤±
    -0.21
    è¯ģ件
    -0.21
    æ®ĭçķĻ
    -0.21
    幸
    -0.20
    çĸµ
    -0.19
    ç¥
    -0.19
    åĪĨåĪ«æĺ¯
    -0.19
    åĵ¥ä»¬
    -0.19
    åħĭæľį
    -0.19
    ä¸ī次
    -0.19
    POSITIVE LOGITS
    çŃĸçķ¥
    0.24
    quette
    0.23
    åĿļæĮģä¸įæĩĪ
    0.20
     strategy
    0.20
    è¿IJèIJ¥
    0.20
    åŀ£
    0.19
     Souls
    0.19
    peat
    0.19
    å®£ä¼ł
    0.19
    hots
    0.19
    Activations Density 0.022%

    No Known Activations