© 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. 2116
    Prev
    Next
    INDEX
    Explanations

    out to

    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
    //----------------------------------------------------------------------------------------------------------------
    -0.21
    Guest
    -0.21
    客人
    -0.20
    pel
    -0.20
    traits
    -0.20
    æīĢåľ¨
    -0.20
    Pel
    -0.20
     delt
    -0.20
    ä¼ļ议室
    -0.20
    tee
    -0.20
    POSITIVE LOGITS
     street
    0.26
     Tonight
    0.24
    _byte
    0.24
    manship
    0.23
    /weather
    0.23
    è¡Ĺ头
    0.23
    åIJĦçķĮ
    0.22
    à¸Ŀà¸Ļ
    0.22
    cape
    0.22
     streets
    0.22
    Activations Density 0.021%

    No Known Activations