© 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. 40064
    Prev
    Next
    INDEX
    Explanations

    locations opposite or facing

    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
    éĻ¤æѤ
    -0.10
    沿çĿĢ
    -0.10
     Ank
    -0.10
     окол
    -0.09
    åĬ£
    -0.09
    åľ°æĸ¹æĶ¿åºľ
    -0.09
    è´«ç©·
    -0.09
    erin
    -0.09
    åĬ©
    -0.09
    笼
    -0.09
    POSITIVE LOGITS
    ä»Ģä¹Īäºĭ
    0.10
     Ùħباشرة
    0.09
    aday
    0.08
    -corner
    0.08
     Shortcut
    0.08
    avad
    0.08
    ä¿Ŀå®Ī
    0.08
    çIJī
    0.08
    sWith
    0.08
    æīĢ说çļĦ
    0.08
    Activations Density 0.011%

    No Known Activations