© 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. 3073
    Prev
    Next
    INDEX
    Explanations

    awards and categories

    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
    aler
    -0.24
    airy
    -0.24
    hoe
    -0.23
    ä¸Ģ个好çļĦ
    -0.23
    roduced
    -0.22
    uters
    -0.22
    ä¸ºæľŁ
    -0.22
    antino
    -0.21
    è¿Ļ两年
    -0.21
    è¿ĻäºĽå¹´
    -0.21
    POSITIVE LOGITS
    å°½
    0.28
    éļIJ
    0.23
    ’in
    0.22
    è¯Ŀ
    0.22
    åľ¨åĨħçļĦ
    0.21
    ä¸Ģäºĭ
    0.21
    åIJĮæł·
    0.21
    åĬłæ²¹
    0.21
    di
    0.21
    'in
    0.21
    Activations Density 0.393%

    No Known Activations