© 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. 2436
    Prev
    Next
    INDEX
    Explanations

    company deal business

    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
    rud
    -0.26
    cient
    -0.26
     Gauss
    -0.25
    åįģåĽĽäºĶ
    -0.24
    ÑĢеб
    -0.23
    æķĻåŃ¦è´¨éĩı
    -0.23
    æĥĩ
    -0.23
    Ctrls
    -0.22
    gmail
    -0.22
     Duch
    -0.22
    POSITIVE LOGITS
     businesses
    0.30
     statewide
    0.28
    _business
    0.27
     business
    0.27
    é£Łåĵģ
    0.26
     retail
    0.26
     marketplace
    0.26
    模å¼ı
    0.26
    å¸Ĥåľº
    0.26
    è¶ħå¸Ĥ
    0.26
    Activations Density 0.004%

    No Known Activations