© 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. 14842
    Prev
    Next
    INDEX
    Explanations

    tub or bath

    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
    å·½
    -0.22
    леп
    -0.21
    loth
    -0.20
    åĪĪ
    -0.20
    ئ
    -0.19
     loạn
    -0.18
    åŃľ
    -0.18
    æ°¸ä¸į
    -0.17
    ä½łè§īå¾Ĺ
    -0.17
     Pap
    -0.17
    POSITIVE LOGITS
    åħ¼
    0.22
    wyn
    0.20
    座
    0.20
    èĩªæĿĢ
    0.20
     Dudley
    0.19
    æ»ļçIJĥ
    0.19
    ä¼ĺéĽħ
    0.18
    кÑĢÑĥÑĤ
    0.18
    aml
    0.18
    çļĦä¼Łå¤§
    0.18
    Activations Density 0.002%

    No Known Activations