© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2520
    Prev
    Next
    INDEX
    Explanations

    business and financial reporting

    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
     myster
    -0.29
     поÑĤом
    -0.28
     mystery
    -0.27
     countless
    -0.27
     magically
    -0.27
     centuries
    -0.27
     зн
    -0.27
     mysterious
    -0.27
     suddenly
    -0.26
     strange
    -0.26
    POSITIVE LOGITS
    稳åģ¥
    0.43
    æĬ¥åijĬæľŁåĨħ
    0.42
    ä¸ĬåįĬå¹´
    0.41
    é¢Ħ计
    0.41
    äºĮåŃ£åº¦
    0.38
    管çIJĨå±Ĥ
    0.37
    è¶ħé¢Ŀ
    0.36
    æĪĺçķ¥
    0.36
    æĪĺçķ¥å¸ĥå±Ģ
    0.36
    è°ĥæķ´
    0.36
    Activations Density 0.036%

    No Known Activations