© 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. 886
    Prev
    Next
    INDEX
    Explanations

    check if condition

    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
    tie
    -0.26
    zell
    -0.23
    eldom
    -0.23
    ä¼ģä¸ļ管çIJĨ
    -0.23
    ialized
    -0.23
    _MSB
    -0.23
    å·²ä¹ħ
    -0.22
    ä»Ģ
    -0.22
     arenas
    -0.22
     abroad
    -0.22
    POSITIVE LOGITS
    æıIJåıĸ
    0.29
     paragraph
    0.27
     prose
    0.26
     excerpt
    0.26
     truth
    0.25
     íĮIJëĭ¨
    0.24
    éĹ®ä»ĸ
    0.24
    æݨçIJĨ
    0.24
     answer
    0.24
     extract
    0.24
    Activations Density 0.026%

    No Known Activations