© 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. 1629
    Prev
    Next
    INDEX
    Explanations

    benefit from

    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
    Putin
    -0.22
     поÑĢÑıдке
    -0.21
    é£İæ³¢
    -0.21
    åŁ¹åħ»åѦçĶŁ
    -0.21
    顾èĻij
    -0.20
    	check
    -0.20
     WARNING
    -0.20
    å³¥
    -0.20
    agine
    -0.19
     Personnel
    -0.19
    POSITIVE LOGITS
     benefit
    0.35
    åıĹçĽĬ
    0.31
     greatly
    0.30
    benef
    0.29
    裨
    0.29
    好å¤Ħ
    0.27
     benefits
    0.27
    å¾ĹçĽĬ
    0.27
     Benefit
    0.27
     benefici
    0.27
    Activations Density 0.020%

    No Known Activations