© 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. 14956
    Prev
    Next
    INDEX
    Explanations

    quoted or apostrophed words

    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
    è¦ģåģļ
    -0.22
     Infos
    -0.19
     ÐIJлекÑģан
    -0.18
    поÑĩ
    -0.17
    è¦ģåľ¨
    -0.17
    /rfc
    -0.16
    è¦ģæĬĬ
    -0.16
    entric
    -0.16
    dit
    -0.16
    anky
    -0.16
    POSITIVE LOGITS
    们çļĦ
    0.23
    们
    0.22
    ãģ¾ãģĹãģ¦
    0.21
    ï¸
    0.21
    ä¹İ
    0.20
    裾
    0.20
    ï¸ı
    0.20
    amp
    0.19
    åĢij
    0.19
    们éĥ½
    0.18
    Activations Density 0.010%

    No Known Activations