© 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. 18626
    Prev
    Next
    INDEX
    Explanations

    geographic and administrative divisions

    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
    å®ı大
    -0.09
    å¤ĸåľ°
    -0.09
    Ỽ
    -0.09
    èŁ¾
    -0.09
    ä¸į足
    -0.08
    绡
    -0.08
    伺
    -0.08
    颤
    -0.08
    ä¸į好
    -0.08
    ãĥ¡ãĥĩãĤ£
    -0.08
    POSITIVE LOGITS
    澳大åĪ©äºļ
    0.11
    åľ¨é¦Ļ港
    0.11
    澳洲
    0.10
    æ¾³
    0.09
    é¦Ļ港
    0.09
    ustralian
    0.09
     Australians
    0.09
     Queensland
    0.09
    Australia
    0.09
     NSW
    0.09
    Activations Density 2.906%

    No Known Activations