© 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. 47601
    Prev
    Next
    INDEX
    Explanations

    salts and ions

    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
    管å§Ķä¼ļ
    -0.09
     Ellison
    -0.09
    grounds
    -0.09
     SLOT
    -0.09
    å§ĭäºİ
    -0.08
     pud
    -0.08
    è¿ĩçļĦ
    -0.08
    æĮ¹
    -0.08
    arith
    -0.08
    çļĦè¶ĭåĬ¿
    -0.08
    POSITIVE LOGITS
    ä¸ĵ项
    0.11
    кÑĢа
    0.09
    osit
    0.09
    çĪ±å°Ķ
    0.09
    _Utils
    0.09
    åŀĭåı·
    0.09
    è§Ħ模æľĢ大
    0.09
     ÑĥпÑĢав
    0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    0.09
    etter
    0.08
    Activations Density 0.151%

    No Known Activations