© 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. 1016
    Prev
    Next
    INDEX
    Explanations

    email headers sender address

    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
    社ä¼ļåıijå±ķ
    -0.25
    ä¼łç»Ł
    -0.24
    ç»Ģ
    -0.24
     пÑĢинÑı
    -0.24
    desktop
    -0.23
     Cop
    -0.23
    ,arg
    -0.23
    è¶ĭåĬ¿
    -0.22
    .BO
    -0.22
    .ng
    -0.22
    POSITIVE LOGITS
    ex
    0.25
     skeletons
    0.24
    heat
    0.23
    urge
    0.23
    æģ»
    0.23
    /Public
    0.22
    unds
    0.22
    æĭĽçĶŁ
    0.21
    icker
    0.21
    lbs
    0.21
    Activations Density 0.010%

    No Known Activations