© 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. 1649
    Prev
    Next
    INDEX
    Explanations

    make file commands

    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
    nic
    -0.25
    .serializer
    -0.24
    ANNEL
    -0.23
    èįīåİŁ
    -0.23
    åĽ½åľŁ
    -0.23
    大éĻĨ
    -0.23
     Cir
    -0.21
    PIX
    -0.21
    erot
    -0.21
    ately
    -0.21
    POSITIVE LOGITS
     chores
    0.30
    干活
    0.28
    å·¥åºı
    0.28
    è¿Ľåº¦
    0.28
     vigor
    0.26
    æĪIJæŀľ
    0.26
    å·¥æľŁ
    0.25
     progression
    0.25
     completion
    0.24
     batching
    0.24
    Activations Density 0.102%

    No Known Activations