© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 79
    Prev
    Next
    INDEX
    Explanations

    biological structures and evolution

    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
     deadline
    -0.28
     taped
    -0.27
     nationwide
    -0.26
     ÑģÑĤÑĢаÑħ
    -0.26
     afternoon
    -0.26
     conversations
    -0.25
     requests
    -0.25
    å³°å̼
    -0.25
    Aware
    -0.25
     churn
    -0.24
    POSITIVE LOGITS
     ancestral
    0.37
     morphology
    0.37
     structures
    0.35
     specialized
    0.35
     evolved
    0.34
    çī©ç§į
    0.34
     structure
    0.33
     specialised
    0.33
    æ¼ĶåĮĸ
    0.33
    primitive
    0.33
    Activations Density 0.267%

    No Known Activations