© 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. 14059
    Prev
    Next
    INDEX
    Explanations

    colors and appearance

    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
    ungi
    -0.23
    omba
    -0.23
    erÃŃa
    -0.22
    åĪĪ
    -0.21
    çĭIJ
    -0.21
    ailles
    -0.21
    æĦŁåıĹ
    -0.20
    etas
    -0.20
    å¥ijåIJĪ
    -0.20
    angs
    -0.20
    POSITIVE LOGITS
    æ¾Ħæ¸ħ
    0.24
    æ¸ħæ¾Ī
    0.21
     görü
    0.21
    ë¹Ľ
    0.19
    æ²īæ·Ģ
    0.19
    filtr
    0.19
    hint
    0.19
     appearance
    0.19
    ä¹ĺçĶ¨è½¦
    0.18
    åĩ¡æľ¬ç½ij
    0.18
    Activations Density 0.016%

    No Known Activations