© 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. 2242
    Prev
    Next
    INDEX
    Explanations

    school year

    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
     lately
    -0.25
     Tyson
    -0.25
     constantly
    -0.24
    ราย
    -0.22
    clr
    -0.22
    å²ģ以ä¸ĭ
    -0.21
    KeyId
    -0.21
    led
    -0.21
    -loop
    -0.21
    è¿ijæľŁ
    -0.21
    POSITIVE LOGITS
    åħ¥åѦ
    0.39
     graduation
    0.35
     undergrad
    0.34
    æ¯įæł¡
    0.33
     undergraduate
    0.33
    æ¯ķä¸ļ
    0.31
    åľ¨åŃ¦æł¡
    0.31
     campus
    0.31
    æ¯ķä¸ļåIJİ
    0.30
     university
    0.30
    Activations Density 0.021%

    No Known Activations