© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 115
    Prev
    Next
    INDEX
    Explanations

    Today's updates and announcements

    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
    åıįä¹ĭ
    -0.27
    å±ŀ
    -0.25
    urally
    -0.24
    æĸ¹åIJij
    -0.23
    iform
    -0.23
    ertos
    -0.22
    (Error
    -0.22
    çĿ¾
    -0.22
     otherwise
    -0.22
    ÑĤеÑĢ
    -0.21
    POSITIVE LOGITS
    ç£
    0.23
    è¿Ļ个æĹ¶ä»£
    0.22
    ale
    0.22
    alian
    0.22
    iram
    0.22
    æĪij以为
    0.22
    &t
    0.21
    -day
    0.21
    ous
    0.20
    alink
    0.20
    Activations Density 0.016%

    No Known Activations