© 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. 12172
    Prev
    Next
    INDEX
    Explanations

    VirtualBox, VMware, Windows

    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
    æİī
    -0.10
    ITT
    -0.09
    æİīäºĨ
    -0.09
    iod
    -0.09
    è¯Ĺ
    -0.09
    æ³ī
    -0.09
    è½»
    -0.09
     IDD
    -0.09
    缺å¸Ń
    -0.09
    oge
    -0.08
    POSITIVE LOGITS
    icket
    0.10
    æĬĬä½ł
    0.09
    achi
    0.08
    ç¾¼
    0.08
    çĮľæµĭ
    0.08
    é¦ĸä½į
    0.08
    åºĸ
    0.08
    åħĪè¿ĽæĬĢæľ¯
    0.08
    åı¯ä»¥æĬĬ
    0.08
    ä¼ļè®©ä½ł
    0.08
    Activations Density 0.089%

    No Known Activations