© 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. 12170
    Prev
    Next
    INDEX
    Explanations

    legal notices

    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
    Not in Any Lists

    No Comments

    Negative Logits
    emble
    -0.09
    åħħ
    -0.09
    åIJĦé¡¹å·¥ä½ľ
    -0.08
    æ®ĸ
    -0.08
    ilde
    -0.08
    ä»°
    -0.08
    Hide
    -0.08
     çı
    -0.08
     hype
    -0.07
    离
    -0.07
    POSITIVE LOGITS
    对æĸ¹
    0.17
    å°įæĸ¹
    0.15
    ç»ĻåĪ«äºº
    0.11
    羣è¯ļ
    0.10
    åıĮæĸ¹
    0.10
    缴è¾ĸ
    0.10
    è¿Ļç§įæĸ¹æ³ķ
    0.09
    æī³
    0.09
     INFORMATION
    0.09
    è®¤çľŁèIJ½å®ŀ
    0.09
    Activations Density 0.069%

    No Known Activations