© 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. 3399
    Prev
    Next
    INDEX
    Explanations

    patent claims

    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
    ç¼Ĩ
    -0.29
     оÑĤдÑĭÑħ
    -0.26
     grocery
    -0.25
     nightlife
    -0.25
     careg
    -0.25
    æķijæĬ¤
    -0.25
     communal
    -0.24
     city
    -0.24
     basketball
    -0.24
    饮éħĴ
    -0.24
    POSITIVE LOGITS
    ä¸ĵåĪ©
    0.43
    åıijæĺİä¸ĵåĪ©
    0.41
     patent
    0.40
     patents
    0.39
     Patent
    0.39
    æ£Ģç´¢
    0.37
    缺éĻ·
    0.32
    审议
    0.30
    çŁ¥è¯Ĩ产æĿĥ
    0.30
    å®¡æŁ¥
    0.30
    Activations Density 0.134%

    No Known Activations