© 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. 11051
    Prev
    Next
    INDEX
    Explanations

    job loss, claims, goods

    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
    建åįİ
    -0.20
    Insensitive
    -0.19
    ä¾ĽéĶĢ
    -0.19
    åħ´
    -0.19
    å½ĵåľ°çļĦ
    -0.19
    è¾ĺ
    -0.19
    ç»ķ
    -0.18
     local
    -0.18
    åıijè´¢
    -0.18
     notified
    -0.18
    POSITIVE LOGITS
    æ¯ıæľĪ
    0.24
    å°±ä¸ļ
    0.23
    è¹Ĵ
    0.21
    æľĪæľ«
    0.20
    å¦ĤæľŁ
    0.20
    _pw
    0.19
    æ¯ı个æľĪ
    0.19
    rees
    0.19
    èĹIJ
    0.19
    æľĪåĪĿ
    0.19
    Activations Density 0.008%

    No Known Activations