© 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. 2689
    Prev
    Next
    INDEX
    Explanations

    changes and updates

    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
     collect
    -0.24
    éĶ¥
    -0.23
     inquiry
    -0.23
     screened
    -0.23
     Inquiry
    -0.23
    询
    -0.23
     shame
    -0.22
     passions
    -0.22
    éĴĵ
    -0.22
     amb
    -0.22
    POSITIVE LOGITS
     changes
    0.65
    _changes
    0.59
    (changes
    0.57
     изменениÑı
    0.57
    çļĦåıĺåĮĸ
    0.56
    Changes
    0.56
    æĽ´æĶ¹
    0.56
     Changes
    0.55
    æĶ¹åĬ¨
    0.55
    changes
    0.53
    Activations Density 0.331%

    No Known Activations