© 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. 17133
    Prev
    Next
    INDEX
    Explanations

    asking questions like how are you

    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
    Negative Logits
    åij£
    -0.20
    åĹIJ
    -0.19
    å½»
    -0.18
    åħ¨æĿij
    -0.18
     usage
    -0.17
    触
    -0.17
     Rach
    -0.17
    åĵĩ
    -0.17
    .addAll
    -0.17
    çļĦéĩįè¦ģæĢ§
    -0.17
    POSITIVE LOGITS
    è¿ĺæľīä»Ģä¹Ī
    0.23
    ä½łè§īå¾Ĺ
    0.22
    æīĵç®Ĺ
    0.21
    ä½łèĩªå·±
    0.20
     Manufact
    0.20
    æĺ¯åIJ¦æľī
    0.19
    ä¸įè§ģ
    0.19
     á»ķn
    0.19
    æľī没æľī
    0.18
    irma
    0.18
    Activations Density 0.026%

    No Known Activations