© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12503
    Prev
    Next
    INDEX
    Explanations

    grams, g, or gm

    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
    NotFoundError
    -0.21
    èµ°å»Ĭ
    -0.20
    ntax
    -0.19
    åŀ®
    -0.18
    éŵ
    -0.17
    arb
    -0.17
     ëĵ
    -0.17
    èģĮä¸ļçĶŁæ¶¯
    -0.17
    ombok
    -0.17
    åĪ³
    -0.17
    POSITIVE LOGITS
    mono
    0.19
    çĴľ
    0.19
    å§Ĩ
    0.19
    _DM
    0.18
    THR
    0.18
    å¡ij
    0.18
    ä¼ģ
    0.17
     dart
    0.17
    close
    0.17
    æł·çļĦ
    0.17
    Activations Density 0.019%

    No Known Activations