© 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. 16007
    Prev
    Next
    INDEX
    Explanations

    hunting

    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
    çĶľçĶľ
    -0.22
    èĪ¹
    -0.21
    éħ¸å¥¶
    -0.21
    æ¼ķ
    -0.20
    èIJĮ
    -0.19
    奶èĮ¶
    -0.19
    èĪ°éĺŁ
    -0.19
    èIJ¥è¿IJ
    -0.19
    stre
    -0.19
    æ´ĹèĦ¸
    -0.19
    POSITIVE LOGITS
    çĭ©
    0.32
    æīĵçĮİ
    0.27
    å°Ħ
    0.26
    å°Ħåĩ»
    0.26
    éĿ¶
    0.24
    éĩİçĶŁåĬ¨çī©
    0.24
    éĩİå¤ĸ
    0.23
    çĮİ
    0.23
    å³Ĵ
    0.23
     hunting
    0.23
    Activations Density 0.026%

    No Known Activations