© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3285
    Prev
    Next
    INDEX
    Explanations

    years ago

    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
    Negative Logits
    UpDown
    -0.24
    åĨįéĢł
    -0.24
    ä¹ĭ家
    -0.24
    宪
    -0.23
    stractions
    -0.23
    /tos
    -0.23
    éĻ¢éĻ¢éķ¿
    -0.22
    apos
    -0.22
    åľĺ
    -0.22
    åıįä¹ĭ
    -0.22
    POSITIVE LOGITS
    zend
    0.29
     давно
    0.28
    çļĦç»ıåħ¸
    0.28
     yet
    0.28
    çļĦèĢģ
    0.27
    å·²ä¹ħ
    0.26
    ernet
    0.25
     vintage
    0.25
     archived
    0.25
    ç»ıåħ¸
    0.23
    Activations Density 0.109%

    No Known Activations