© 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. 827
    Prev
    Next
    INDEX
    Explanations

    food and cooking times

    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
    éĻªåIJĮ
    -0.25
    æĪ·
    -0.25
     prop
    -0.25
     fairness
    -0.22
    å¥łå®ļäºĨ
    -0.22
    -of
    -0.21
    ä¸ĩæĪ·
    -0.21
     partnership
    -0.21
    kip
    -0.21
    诸å¦Ĥ
    -0.21
    POSITIVE LOGITS
     halves
    0.27
    _ALIGN
    0.26
    bane
    0.24
     fragments
    0.23
    _extraction
    0.23
    æıIJåıĸ
    0.23
     initially
    0.22
    åıĸåĩº
    0.22
    hợ
    0.22
    æĭ¿åĩº
    0.22
    Activations Density 0.034%

    No Known Activations