© 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. 15263
    Prev
    Next
    INDEX
    Explanations

    October, Published, Caption, Retail

    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
    IPAddress
    -0.19
    bert
    -0.19
     PSP
    -0.19
     kot
    -0.18
    Æ°á»Ŀ
    -0.18
    BERT
    -0.18
    bor
    -0.17
    ody
    -0.17
     sublist
    -0.17
    _EXTENSION
    -0.17
    POSITIVE LOGITS
    æľ¬æĬ¥è®¯
    0.25
    åŃĹåı·
    0.24
    _RAD
    0.24
    ä¹ĭåĬ¿
    0.21
    éĹ²ç½®
    0.20
    æľ¬æĬ¥
    0.20
    çĪ½
    0.19
    von
    0.19
    lint
    0.19
    头æĿ¡
    0.19
    Activations Density 0.192%

    No Known Activations