© 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. 312
    Prev
    Next
    INDEX
    Explanations

    Year, Friday, ball, games

    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
    fore
    -0.24
    åŁİå¸ĤçļĦ
    -0.23
    åģļçļĦäºĭ
    -0.23
    çĶ·å£«
    -0.22
    头åıij
    -0.21
    unft
    -0.21
    æĮĤçĿĢ
    -0.21
    ResponseBody
    -0.21
    éľ°
    -0.21
    decltype
    -0.21
    POSITIVE LOGITS
    åīįå¤ķ
    0.22
     Rice
    0.21
     Lies
    0.21
    yers
    0.21
     prohibit
    0.20
    getRoot
    0.20
     Complex
    0.20
     brew
    0.20
    讲述
    0.20
    ä¸įå®ļ
    0.20
    Activations Density 0.002%

    No Known Activations