© 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. 1067
    Prev
    Next
    INDEX
    Explanations

    carbonated beverages, sparkling wine, pressurized

    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
    æľīçĶ¨çļĦ
    -0.26
    -resources
    -0.26
    å¹´èĸª
    -0.24
    STE
    -0.24
     Karn
    -0.24
    ForResource
    -0.23
    榱
    -0.23
    icum
    -0.23
     Resource
    -0.23
    é»ijå¤ľ
    -0.23
    POSITIVE LOGITS
     bubbles
    0.31
    eration
    0.31
    ä¸ĭæ²ī
    0.28
    .inject
    0.28
    æ°
    0.27
    atur
    0.26
    inject
    0.26
     agitation
    0.25
    éĨª
    0.25
     injected
    0.25
    Activations Density 0.007%

    No Known Activations