© 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. 15213
    Prev
    Next
    INDEX
    Explanations

    year, age, birthday

    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
     reign
    -0.20
    è¿ŀäºij
    -0.20
    _BU
    -0.20
     bè
    -0.19
     cup
    -0.19
    MAS
    -0.18
    PageRoute
    -0.18
    -zA
    -0.18
    åīį身
    -0.18
    çģ«çĥŃ
    -0.17
    POSITIVE LOGITS
    æ²Ł
    0.21
    osi
    0.20
    æĦŁåı¹
    0.19
    ä»Ĭå¹´
    0.19
    xmm
    0.19
    éľĩ
    0.19
    olini
    0.18
    æī¹éĩı
    0.18
    溪
    0.18
    ossal
    0.18
    Activations Density 0.013%

    No Known Activations