© 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. 2373
    Prev
    Next
    INDEX
    Explanations

    Rugby league, attorneys general, Studio Code, jQuery Mobile

    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
    ROID
    -0.23
    å½·
    -0.23
    ENO
    -0.22
    æĹ¥å¸¸çĶŁæ´»
    -0.22
    .library
    -0.22
    éĽªèĬ±
    -0.22
    INTERN
    -0.21
    /end
    -0.21
    طا
    -0.21
    åĺ´åĶĩ
    -0.20
    POSITIVE LOGITS
    edo
    0.24
    illion
    0.24
    pst
    0.22
    .Tasks
    0.22
     medically
    0.22
    æĢİä¹Īåģļ
    0.22
    请大家
    0.21
     intellectually
    0.20
    nio
    0.20
    éĥ¨ç½²
    0.20
    Activations Density 0.578%

    No Known Activations