© 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. 1132
    Prev
    Next
    INDEX
    Explanations

    interferometer, side-by-side, sandwich, tricycle, shell, reflex, bola

    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
    èĥ½åĬĽå¼º
    -0.25
    âĤ¬âĦ¢
    -0.24
    eni
    -0.24
    Standing
    -0.23
     uncont
    -0.23
    vir
    -0.21
    FACT
    -0.21
    è¹ĭ
    -0.21
     vigil
    -0.21
    standing
    -0.21
    POSITIVE LOGITS
     structure
    0.34
    ç»ĵæŀĦ
    0.33
    æŀ¶æŀĦ
    0.33
     architecture
    0.32
     consisting
    0.32
    æĪĸå¤ļ
    0.32
    åĪĨ离
    0.31
    æł¼å±Ģ
    0.31
    åŀĭ
    0.31
     dual
    0.30
    Activations Density 0.490%

    No Known Activations