© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13108
    Prev
    Next
    INDEX
    Explanations

    INSERT INTO

    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
    ee
    -0.19
    enn
    -0.19
    vere
    -0.19
     pur
    -0.18
    Pale
    -0.18
    pace
    -0.18
    tsy
    -0.18
    awe
    -0.18
    wer
    -0.18
    isk
    -0.18
    POSITIVE LOGITS
    åĴ½
    0.23
    åĹ
    0.22
    nop
    0.21
    åĨĽäºĭ
    0.21
    ç»ıèIJ¥æ¨¡å¼ı
    0.21
    æŁ¥çľĭæĽ´å¤ļ
    0.21
    çĤĬ
    0.20
    è¿ĩåī©
    0.20
    综åIJĪå®ŀåĬĽ
    0.20
    çĤ¹æ»´
    0.20
    Activations Density 0.006%

    No Known Activations