© 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. 15397
    Prev
    Next
    INDEX
    Explanations

    share freely or information

    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
    éĴĿ
    -0.19
    åĪĨåŃIJ
    -0.19
    å¤ļå±Ĥ次
    -0.17
    gen
    -0.17
    ted
    -0.17
    åŁºæķ°
    -0.17
    ual
    -0.16
    go
    -0.16
    åĮĸèĤ¥
    -0.15
    eki
    -0.15
    POSITIVE LOGITS
    ç»Ļ大家
    0.22
     secrets
    0.21
    ç»ıéªĮåĴĮ
    0.20
     פע×ķ׾×Ķ
    0.20
    wealth
    0.19
    abouts
    0.18
    æѤåĪ»
    0.18
    ãĤĪãģĨãģª
    0.18
     ÑĢеÑĨеп
    0.18
     experience
    0.18
    Activations Density 0.067%

    No Known Activations