© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60566
    Prev
    Next
    INDEX
    Explanations

    walls of structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    è¿ĻæĶ¯
    -0.09
    è§īéĨĴ
    -0.09
    ä¸Ģ份
    -0.09
    projects
    -0.09
    èİĺ
    -0.09
    仪
    -0.09
    çĹ£
    -0.09
    ç¾İæĦŁ
    -0.09
     Arr
    -0.08
    稿
    -0.08
    POSITIVE LOGITS
     walls
    0.28
    å¢Ļå£ģ
    0.25
     Walls
    0.25
    å¢Ļä½ĵ
    0.23
    walls
    0.23
    å¢Ļ
    0.22
     ÑģÑĤен
    0.22
     wall
    0.21
    å¢ĻéĿ¢
    0.21
    å£ģ
    0.21
    Activations Density 0.112%

    No Known Activations