© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3307
    Prev
    Next
    INDEX
    Explanations

    way back or directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ayer
    -0.23
    æ·¡åĮĸ
    -0.22
     Tablet
    -0.22
    çīĮåŃIJ
    -0.21
     Prev
    -0.21
     brands
    -0.21
    quam
    -0.21
    çĶ«
    -0.20
    éĥ¨ä½į
    -0.20
    ë¹Ħ
    -0.20
    POSITIVE LOGITS
    iture
    0.26
     itinerary
    0.25
    å¿ħè¦ģ
    0.24
     destination
    0.23
    æĬ¥ä»·
    0.22
    xin
    0.22
    æĪĸå¤ļ
    0.22
    åĩŃ
    0.21
    æİĪ
    0.21
     mission
    0.21
    Activations Density 0.005%

    No Known Activations