© 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. 48933
    Prev
    Next
    INDEX
    Explanations

    place names ending in istan

    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
    éĺ´
    -0.08
    çİĭåĽ½
    -0.08
    çİ°
    -0.08
    çİ°ä»»
    -0.07
    è¹Ī
    -0.07
     thủ
    -0.07
    çģı
    -0.07
     Howe
    -0.07
    arry
    -0.07
    ä½£
    -0.07
    POSITIVE LOGITS
    è¾ħ
    0.11
    è¼Ķ
    0.11
    解æĶ¾æĢĿæĥ³
    0.10
     дог
    0.09
    ITCH
    0.09
    ä¼ļåIJĮ
    0.09
    å¤ĸæĿ¥
    0.09
    ä¸Ģéģĵ
    0.09
    è¾ħ导
    0.09
    okus
    0.09
    Activations Density 0.001%

    No Known Activations