© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 503
    Prev
    Next
    INDEX
    Explanations

    worldwide license, similar technologies, sell software, every year, effects of

    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
    以èī²
    -0.25
    æµĵæµĵçļĦ
    -0.25
    hits
    -0.24
    宣讲
    -0.23
     hitting
    -0.23
    hos
    -0.22
    æµĵæµĵ
    -0.22
    ç»ĻæĤ¨
    -0.21
     Lonely
    -0.21
     learners
    -0.21
    POSITIVE LOGITS
    ä¸ĢåĪĩ
    0.27
    è¡į
    0.27
     whatever
    0.26
     whatsoever
    0.25
    çļĦæīĢæľī
    0.24
    çļĦä¸ĢåĪĩ
    0.24
     derivative
    0.23
     derivatives
    0.23
     diverse
    0.23
     Äijá»ĩ
    0.23
    Activations Density 0.041%

    No Known Activations