© 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. 260
    Prev
    Next
    INDEX
    Explanations

    young family or religious figures

    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
    åħ¨ç¨ĭ
    -0.26
     Mobil
    -0.24
     matter
    -0.23
    妯
    -0.23
     Matter
    -0.23
     Gallagher
    -0.22
     Pru
    -0.22
    å§ijå¨ĺ
    -0.22
    adow
    -0.22
    ment
    -0.22
    POSITIVE LOGITS
    æ¡ĮåŃIJ
    0.23
    Seats
    0.23
    åī²
    0.23
    Servi
    0.23
    çªij
    0.23
     Labs
    0.22
    æī¼
    0.22
     downstairs
    0.22
    æİ£
    0.22
    small
    0.22
    Activations Density 0.005%

    No Known Activations