© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10682
    Prev
    Next
    INDEX
    Explanations

    pressing, moving, shaking, pinching

    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
    æ®ļ
    -0.22
    说çļĦæĺ¯
    -0.19
    .TXT
    -0.19
    é¼¾
    -0.19
    roe
    -0.19
    anes
    -0.19
    atron
    -0.19
    èł¡
    -0.18
    æģĤ
    -0.18
    atoes
    -0.18
    POSITIVE LOGITS
    使åħ¶
    0.23
    å°ıå¿ĥ
    0.22
    ä¸Ģä¸ĭ
    0.21
     thả
    0.21
     ÑĩÑĤобÑĭ
    0.19
    imeo
    0.19
    ç»ĻåŃ©åŃIJ
    0.18
    åĬĽåº¦
    0.18
    ä½łä¼ļåıijçİ°
    0.18
    è§īå¾Ĺå¾Ī
    0.18
    Activations Density 0.021%

    No Known Activations