© 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. 23976
    Prev
    Next
    INDEX
    Explanations

    Mediterranean region

    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
    tober
    -0.10
    æīĢåľ¨åľ°
    -0.09
    /avatar
    -0.09
    çīĮ
    -0.08
    asher
    -0.08
    iture
    -0.08
    ÑģÑĤа
    -0.08
    ç½´
    -0.08
    OTH
    -0.08
    Gram
    -0.08
    POSITIVE LOGITS
    é£İåħī
    0.11
    åĪijèѦ
    0.11
    çĶŁçĶŁ
    0.10
    ALLY
    0.10
    æ¾¹
    0.10
    çĶŁäº§æĢ»åĢ¼
    0.10
    峤
    0.09
    çĭİ
    0.09
    alte
    0.09
    aly
    0.09
    Activations Density 0.007%

    No Known Activations