© 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. 11870
    Prev
    Next
    INDEX
    Explanations

    cockroach or sexually explicit content

    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
    ãĤĪãģĨãģª
    -0.17
    ftime
    -0.16
    æĶ»åĬ¿
    -0.15
    ¡
    -0.15
     Redistributions
    -0.15
    主ä¹īæĢĿæĥ³
    -0.15
    ãģıãĤĮ
    -0.14
    äºĨä¸Ģåı¥
    -0.14
    æŶæŶ
    -0.14
    ëĮĢíķĻ
    -0.14
    POSITIVE LOGITS
    ingly
    0.24
    ening
    0.24
    ness
    0.24
    ãģĹãģ¾ãģĦ
    0.21
    ering
    0.20
    manship
    0.20
    ean
    0.20
    ees
    0.20
    uard
    0.18
    å¨ĺ
    0.18
    Activations Density 0.015%

    No Known Activations