© 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. 1747
    Prev
    Next
    INDEX
    Explanations

    primitive composition

    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
    åĬŁåĬĽ
    -0.27
     Rect
    -0.26
     Grid
    -0.25
     Valve
    -0.25
     frontend
    -0.24
    åĢļ
    -0.23
     ITV
    -0.23
    éļľç¢į
    -0.23
    åģľçĶµ
    -0.23
    娱ä¹IJ
    -0.22
    POSITIVE LOGITS
    éĻ¨
    0.34
     fragments
    0.31
    åĽŀæĶ¶
    0.29
    æł·æľ¬
    0.29
     experiment
    0.29
    ä¸ŃåIJ«æľī
    0.28
    æł·åĵģ
    0.28
     samples
    0.28
    æĪIJåĪĨ
    0.28
     collections
    0.28
    Activations Density 0.012%

    No Known Activations