© 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. 14341
    Prev
    Next
    INDEX
    Explanations

    style, strength, design, woman, material

    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
    .mvc
    -0.23
    inherit
    -0.21
    åĶł
    -0.20
    é£İåı£
    -0.20
    _highlight
    -0.20
     Tomorrow
    -0.19
    _CHAN
    -0.19
     inheritance
    -0.18
    .lu
    -0.18
    é«ĺå³°
    -0.18
    POSITIVE LOGITS
    åı¯èĥ½æĺ¯
    0.29
    æĺ¾çĦ¶æĺ¯
    0.28
    好åĥıæĺ¯
    0.27
    ä¸Ģå®ļæĺ¯
    0.25
    èĤ¯å®ļæĺ¯
    0.25
    åºĶ该æĺ¯
    0.25
    æĺ¾çĦ¶
    0.24
    å¾Īæľīåı¯èĥ½
    0.24
    å¾Īåı¯èĥ½
    0.24
    åĩºçİ°åľ¨
    0.24
    Activations Density 0.253%

    No Known Activations