© 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. 3116
    Prev
    Next
    INDEX
    Explanations

    new age and future events

    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
    æĬµ
    -0.09
    åĩī
    -0.09
    è§Ħ磩
    -0.09
     dân
    -0.08
    iores
    -0.08
    çIJ¦
    -0.08
     Slee
    -0.08
    ç¥ļ
    -0.08
    ä¸įå°ij人
    -0.08
    â¼
    -0.08
    POSITIVE LOGITS
    åį¦
    0.11
    宫
    0.10
    ç±½
    0.09
    æĻ®æŁ¥
    0.09
    abet
    0.09
    棵æłij
    0.09
    èľ¡
    0.09
    è°
    0.09
    å®®
    0.08
    cano
    0.08
    Activations Density 0.061%

    No Known Activations