© 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. 16611
    Prev
    Next
    INDEX
    Explanations

    bringing or taking someone/something

    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
    nty
    -0.20
     voiced
    -0.19
    _factors
    -0.19
    itution
    -0.19
    ä¸ĸçķĮ第ä¸Ģ
    -0.18
    è¡¿
    -0.18
    пи
    -0.18
    èıŁ
    -0.18
    stance
    -0.17
    åĬªåĬĽ
    -0.17
    POSITIVE LOGITS
    åŃ©åŃIJ
    0.25
    æĪijåİ»
    0.25
    大家ä¸Ģèµ·
    0.23
    家人
    0.23
     деÑĤей
    0.22
    èĩªæľī
    0.21
    åĩºå¢ĥ
    0.21
     Keys
    0.20
    éĴ¥åĮĻ
    0.20
    åŃIJãģ©ãĤĤ
    0.20
    Activations Density 0.025%

    No Known Activations