© 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. 2747
    Prev
    Next
    INDEX
    Explanations

    connected to something

    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
    æĩĤ
    -0.28
    âm
    -0.25
    åĵģ
    -0.25
    é¢Ŀ
    -0.24
    amac
    -0.24
    åħħæĸ¥
    -0.23
    åĨµ
    -0.23
    èī°
    -0.23
    éĻIJæŶ
    -0.23
    讫
    -0.23
    POSITIVE LOGITS
    纽带
    0.45
    è¿ŀæİ¥
    0.39
    缸è¿ŀ
    0.38
     ná»iji
    0.37
     connecting
    0.36
     connected
    0.36
     ìĹ°ê²°
    0.35
     adjacent
    0.35
    (connect
    0.35
    -connected
    0.34
    Activations Density 0.048%

    No Known Activations