© 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. 1798
    Prev
    Next
    INDEX
    Explanations

    at the moment

    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
    ooks
    -0.21
    åįĥåı¤
    -0.21
    riba
    -0.21
    è´ŁéĿ¢å½±åĵį
    -0.20
    è¦ģçĤ¹
    -0.20
    对è¯Ŀ
    -0.20
    注æĦıäºĭ项
    -0.20
    æİĮ声
    -0.20
    æĸĭ
    -0.20
    outine
    -0.19
    POSITIVE LOGITS
    åĦ¿
    0.27
    eer
    0.26
    ness
    0.24
    hood
    0.24
    åĮĸè¿Ľç¨ĭ
    0.23
    itude
    0.23
    eur
    0.23
    e
    0.23
    amiento
    0.23
    ein
    0.23
    Activations Density 0.020%

    No Known Activations