© 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. 3066
    Prev
    Next
    INDEX
    Explanations

    financial institutions and banking

    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
    Not in Any Lists

    No Comments

    Negative Logits
     unheard
    -0.27
    åıĮèĦļ
    -0.24
     обÑĥÑĩениÑı
    -0.24
     EVENT
    -0.23
     interviewing
    -0.23
     tast
    -0.23
     Basketball
    -0.23
    åĴĦ
    -0.23
     ÑĦигÑĥÑĢ
    -0.22
    æ´½è°Ī
    -0.22
    POSITIVE LOGITS
     weak
    0.27
    æķ´é¡¿
    0.26
     weakened
    0.26
    èĦĨå¼±
    0.25
    å¼±
    0.25
    éĹ´
    0.25
    åĨħéĥ¨
    0.24
    -dominated
    0.24
    å¤įèĭı
    0.24
    èµĦäº§è´ŁåĢº
    0.24
    Activations Density 0.018%

    No Known Activations