© 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. 2524
    Prev
    Next
    INDEX
    Explanations

    prostate cancer

    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
    轻微
    -0.36
    ffe
    -0.28
    æķ£æŃ¥
    -0.24
    FFE
    -0.24
    æĭįæĭį
    -0.24
     padx
    -0.23
    çݯå¢ĥåį«çĶŁ
    -0.23
    å°ıå°ıçļĦ
    -0.23
    ãĥķãĥªãĥ¼
    -0.23
     slight
    -0.23
    POSITIVE LOGITS
    å·¨åŀĭ
    0.44
    å·¨é¢Ŀ
    0.43
    顶级
    0.41
    è¶ħ级
    0.36
    æŀģé«ĺ
    0.35
    huge
    0.34
    è¶ħé«ĺ
    0.34
     colossal
    0.33
     mega
    0.33
    çļĦ巨大
    0.33
    Activations Density 0.968%

    No Known Activations