© 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. 23966
    Prev
    Next
    INDEX
    Explanations

    proximity or closeness

    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
    åIJĦèĩª
    -0.10
    astro
    -0.10
    íĴĢ
    -0.09
    èµ·æŃ¥
    -0.09
     Schro
    -0.09
     Dort
    -0.08
     Tourism
    -0.08
    æĬĹæĪĺ
    -0.08
    addon
    -0.08
    .transition
    -0.08
    POSITIVE LOGITS
    éĿłè¿ij
    0.26
    è¿ijè·Ŀ离
    0.24
     clos
    0.23
     proximity
    0.23
    æİ¥è¿ij
    0.23
    è´´è¿ij
    0.23
     closest
    0.21
    亲è¿ij
    0.20
    èµ°è¿ij
    0.20
     close
    0.20
    Activations Density 0.090%

    No Known Activations