© 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. 11946
    Prev
    Next
    INDEX
    Explanations

    cohorts and generations

    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
    æijĨ
    -0.24
    æĶ¾è¿ĩ
    -0.23
    ä¸ĢéŨ
    -0.23
    å½ĵåľ°
    -0.21
    å½ĵåľ°æĶ¿åºľ
    -0.20
    _Var
    -0.20
    è¿Ļæĺ¯ä¸Ģç§į
    -0.20
    ä»»ä½ķå½¢å¼ı
    -0.20
    ãģĦãĤį
    -0.19
    ä¸ī天
    -0.19
    POSITIVE LOGITS
     era
    0.22
    fer
    0.21
    åĴ»
    0.21
    æĹ¶ä»£çļĦ
    0.21
    年代
    0.21
    -era
    0.20
    elf
    0.20
    맥
    0.20
    icus
    0.20
     hur
    0.19
    Activations Density 0.010%

    No Known Activations