© 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. 3352
    Prev
    Next
    INDEX
    Explanations

    get to know

    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
    社ä¼ļå®ŀè·µ
    -0.23
    ä»Ģä¹Īéĥ½ä¸į
    -0.22
    俸
    -0.22
    çĮ®è¡Ģ
    -0.21
    æİī
    -0.20
    æݩ饰
    -0.20
    åıłåĬł
    -0.20
    宣åijĬ
    -0.20
    esium
    -0.19
    æĭ¬
    -0.19
    POSITIVE LOGITS
     anew
    0.28
     acquainted
    0.28
     stranger
    0.24
    åĴĮå®ĮåĸĦ
    0.24
    rlen
    0.24
    paces
    0.24
     neighbors
    0.24
     fellow
    0.23
    å½¼æѤ
    0.23
     intimately
    0.23
    Activations Density 0.007%

    No Known Activations