© 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. 55527
    Prev
    Next
    INDEX
    Explanations

    located or location

    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
    以èī²
    -0.10
    ç³Ł
    -0.10
    ä¸Ģé¡¿
    -0.09
    otch
    -0.09
    ä¸Ńè¶ħ
    -0.09
    æĪij说
    -0.09
    à¹Īà¸Ńà¸ĩ
    -0.08
    翻身
    -0.08
    orde
    -0.08
     вÑĭп
    -0.08
    POSITIVE LOGITS
    ä½įäºİ
    0.25
     located
    0.22
    located
    0.20
     ÑĢаÑģполож
    0.19
    ä½įæĸ¼
    0.18
     location
    0.18
    åĿIJèIJ½
    0.18
    ä½įç½®
    0.17
    åľ°çĤ¹
    0.17
    åĿIJèIJ½äºİ
    0.17
    Activations Density 0.196%

    No Known Activations