© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 370
    Prev
    Next
    INDEX
    Explanations

    search engines and online services

    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
    AdminController
    -0.25
    éĵ¾æĿ¡
    -0.25
     SpaceX
    -0.25
    è£ħå¤ĩåĪ¶éĢł
    -0.23
    è£ħå¤ĩ
    -0.23
     constexpr
    -0.23
    éĻIJéĩı
    -0.23
    odont
    -0.23
    顺丰
    -0.23
    Specifier
    -0.23
    POSITIVE LOGITS
    Yahoo
    0.41
     Yahoo
    0.40
    .yahoo
    0.35
    æIJľç´¢å¼ķæĵİ
    0.34
     yahoo
    0.34
     search
    0.34
    ä¸Ĭç½ij
    0.34
    æIJľç´¢
    0.33
    主页
    0.31
     searches
    0.30
    Activations Density 0.029%

    No Known Activations