© 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. 2813
    Prev
    Next
    INDEX
    Explanations

    metaphor or analogy

    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
    _generated
    -0.25
    utow
    -0.24
     garner
    -0.23
     Monster
    -0.23
     nomin
    -0.22
    capitalize
    -0.22
    第ä¸ĢæĿ¡
    -0.22
    Generated
    -0.22
    norm
    -0.22
    ä¼łçľŁ
    -0.22
    POSITIVE LOGITS
    æ¯Ķåĸ»
    0.81
     analogy
    0.74
     metaphor
    0.69
    åĸ»
    0.59
     analog
    0.52
    èѬ
    0.50
     liken
    0.47
     Analog
    0.45
    形象
    0.43
     metaph
    0.40
    Activations Density 0.127%

    No Known Activations