© 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. 16769
    Prev
    Next
    INDEX
    Explanations

    after coma or hangups

    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
    åį±
    -0.20
    uries
    -0.20
    姥姥
    -0.20
    è¥ģ
    -0.20
    社ä¼ļä¿Ŀéļľ
    -0.20
    ç«ĻçĿĢ
    -0.19
    裤
    -0.19
     toc
    -0.19
    RCT
    -0.19
    Ñģка
    -0.19
    POSITIVE LOGITS
    éĨĴæĿ¥
    0.28
     aftermath
    0.24
    第äºĮ天
    0.23
    è¿ĩåIJİ
    0.21
     effects
    0.20
    çĹķ
    0.20
    lena
    0.19
    -effects
    0.19
    effects
    0.19
    æķĪåºĶ
    0.19
    Activations Density 0.008%

    No Known Activations