© 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. 3426
    Prev
    Next
    INDEX
    Explanations

    Wall Street Journal reports

    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
    çĮ®
    -0.25
    apk
    -0.24
    æŶèĬĤ
    -0.23
    çĶļ
    -0.23
    uts
    -0.23
    å±ħ
    -0.23
    mysqli
    -0.23
    (tasks
    -0.22
    çį»
    -0.22
     Alger
    -0.21
    POSITIVE LOGITS
    ä¸ŃåĽ½ä¼ģä¸ļ
    0.31
    ä¼ģä¸ļ
    0.26
     subscriber
    0.26
    æŁľåı°
    0.26
    è¯ģåĪ¸äº¤æĺĵ
    0.25
    ä¿¡æģ¯æĬ«éľ²
    0.25
     Probe
    0.25
     priv
    0.25
    probe
    0.25
     reporters
    0.25
    Activations Density 0.023%

    No Known Activations