© 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. 18000
    Prev
    Next
    INDEX
    Explanations

    friend's house or place

    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
    neau
    -0.08
    æĹłäººé©¾é©¶
    -0.08
    ä»İäºĭ
    -0.08
    æŀ¯çĩ¥
    -0.07
    çIJ¬
    -0.07
    çŀĦåĩĨ
    -0.07
    argent
    -0.07
    让å®ĥ
    -0.07
    æµĵ
    -0.07
    è¨Ģ论
    -0.07
    POSITIVE LOGITS
    客æĪ·çļĦ
    0.11
    家éĩĮ
    0.10
    æĭľè®¿
    0.10
    客
    0.10
     방문
    0.10
    訪
    0.09
    访
    0.09
     visit
    0.09
    家ä¸Ń
    0.09
     visite
    0.09
    Activations Density 0.044%

    No Known Activations