© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 32820
    Prev
    Next
    INDEX
    Explanations

    regions from central europe

    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
    éĤĵå°ıå¹³
    -0.08
    稳åģ¥
    -0.08
    åħ¬å®īå±Ģ
    -0.08
    èĤ¯
    -0.08
    alling
    -0.08
    buat
    -0.08
    hat
    -0.08
    çķ²
    -0.07
    æŀ¯
    -0.07
    æİ¥åĪ°
    -0.07
    POSITIVE LOGITS
    .appspot
    0.10
    åİĿ
    0.09
    弧
    0.09
    IMIT
    0.09
    央ä¼ģ
    0.09
    à¸ļรร
    0.08
     Corpus
    0.08
    å¿«
    0.08
    缴è¾ĸå¸Ĥ
    0.08
     اÙĦØ£ÙĦÙħ
    0.08
    Activations Density 0.105%

    No Known Activations