© 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. 3378
    Prev
    Next
    INDEX
    Explanations

    possible tenants, lower overhead, wedding frequenters

    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
    æıIJ款
    -0.24
    åĵºä¹³
    -0.22
    æĮĩè´£
    -0.22
    лиÑĨ
    -0.22
    atham
    -0.21
    _HTML
    -0.21
     Wide
    -0.21
    'l
    -0.21
    æıIJåIJį
    -0.20
     Kv
    -0.20
    POSITIVE LOGITS
    为æĤ¨
    0.30
    å¸¦ä½ł
    0.29
    è·Łä½ł
    0.26
    ç»ĻæĤ¨
    0.26
    æŃ£åľ¨è¿Ľè¡Į
    0.24
     servicing
    0.24
    å¯¹ä½ł
    0.24
    ç»Ļä½ł
    0.23
    æķĻä½ł
    0.23
    带走
    0.23
    Activations Density 0.427%

    No Known Activations