© 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. 12148
    Prev
    Next
    INDEX
    Explanations

    specificity

    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
    æŃ£å½ĵ
    -0.10
    ä¸ĢèĪ¬æĺ¯
    -0.09
    å®īæħ°
    -0.09
    .px
    -0.09
    æ²ģ
    -0.09
    鼶ç¢İ
    -0.09
    åIJĮå¿ĥ
    -0.09
    侪
    -0.08
    å·¥ç¨ĭæĬĢæľ¯
    -0.08
    æĽĻåħī
    -0.08
    POSITIVE LOGITS
    specific
    0.11
    æĺ¯å¦Ĥä½ķ
    0.11
     specifically
    0.10
    éĤ£ä»½
    0.09
    Specific
    0.09
     ones
    0.09
    为æĬĵ
    0.09
    以ä¸ĭåĩłä¸ª
    0.08
    å¦Ĥä½ķ
    0.08
    ä½ľèĢħæľ¬äºº
    0.08
    Activations Density 0.188%

    No Known Activations