© 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. 58027
    Prev
    Next
    INDEX
    Explanations

    locations or geographic areas

    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
    åŃĺåľ¨äºİ
    -0.10
    éĻĽä¸ĭ
    -0.09
     PROVIDED
    -0.09
    åĩºéģĵ
    -0.09
     yaÅŁan
    -0.09
    ä½ıåľ¨
    -0.09
    à¸ŀระราà¸Ĭ
    -0.09
    åıijçĶŁåľ¨
    -0.09
    éľĦ
    -0.08
    åľ¨åħ¨åĽ½
    -0.08
    POSITIVE LOGITS
    æŶè£ħ
    0.10
    éķĽ
    0.09
    avery
    0.09
    ạt
    0.09
    è¿IJè´¹
    0.09
    ague
    0.09
    isci
    0.08
     Dud
    0.08
     Aires
    0.08
    常çĶ¨
    0.08
    Activations Density 0.087%

    No Known Activations