© 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. 14790
    Prev
    Next
    INDEX
    Explanations

    delivered on, days ago, my hands

    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
     reversible
    -0.22
     inher
    -0.21
    æĴ¼
    -0.21
    çIJĨ念
    -0.20
    åĽŀå½Ĵ
    -0.20
    ä¸İä¼Ĺä¸įåIJĮ
    -0.20
    è¿İåIJĪ
    -0.19
    åĬ¨æijĩ
    -0.19
    æīĽ
    -0.19
    åı£åı·
    -0.19
    POSITIVE LOGITS
    å¾ij
    0.29
    å¾Ħ
    0.28
    sender
    0.27
    éĤ®ä»¶
    0.26
    éĢļçŁ¥
    0.26
    åıijéĢģ
    0.25
    æİ¥æĶ¶
    0.25
     sender
    0.24
    .sender
    0.24
    派人
    0.23
    Activations Density 0.082%

    No Known Activations