© 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. 16235
    Prev
    Next
    INDEX
    Explanations

    ending sentences with right?

    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
    çİĭåĽ½
    -0.19
    boro
    -0.19
    lip
    -0.19
    atsu
    -0.19
     ÑģооÑĤвеÑĤ
    -0.18
    两ç§į
    -0.18
    _DLL
    -0.18
    åĽĽç§į
    -0.18
    å©Ĩ
    -0.17
     Hyde
    -0.17
    POSITIVE LOGITS
    ØŁ
    0.25
    ï¼Ł
    0.23
    没éĶĻ
    0.21
    entin
    0.19
    ï¼Ł↵↵
    0.18
    atham
    0.18
    è¹
    0.18
    /Library
    0.17
    ï¼Ł↵
    0.17
    èĢģ人家
    0.17
    Activations Density 0.015%

    No Known Activations