© 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. 11848
    Prev
    Next
    INDEX
    Explanations

    geology and geological contexts

    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
    itous
    -0.18
    ãģ£ãģįãĤĬ
    -0.17
    å²Ļ
    -0.17
    iesen
    -0.16
    stick
    -0.16
    ãģģ
    -0.16
    çĶµéĩı
    -0.16
     Åŀe
    -0.16
    cede
    -0.16
    ativ
    -0.16
    POSITIVE LOGITS
    éģĹ迹
    0.19
    çģ¾å®³
    0.18
    åľ°è²Į
    0.18
    ruk
    0.17
    æ·±è¿ľ
    0.17
    å²©çŁ³
    0.17
    éĩĩçŁ¿
    0.17
    岩
    0.17
    çĶŁäº§æĢ»åĢ¼
    0.16
    ema
    0.16
    Activations Density 0.008%

    No Known Activations