© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15145
    Prev
    Next
    INDEX
    Explanations

    World Records, Institute of Technology, Twitpic

    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
    inia
    -0.22
    Ñģкие
    -0.20
    åħħåĪĨåıijæĮ¥
    -0.19
    atics
    -0.19
    antly
    -0.19
    pections
    -0.18
    âĬ¿
    -0.18
    íģ¼
    -0.18
    äºĮæīĭ
    -0.18
    è¶Ł
    -0.18
    POSITIVE LOGITS
    URAL
    0.20
    APA
    0.19
    æīĭå·¥
    0.19
    饲
    0.18
    ç¥Ń
    0.18
    è¾ĵç»Ļ
    0.18
    个
    0.18
    æ´Ĺå¹²åĩĢ
    0.17
     min
    0.17
    æ¡¥
    0.17
    Activations Density 0.003%

    No Known Activations