© 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. 55650
    Prev
    Next
    INDEX
    Explanations

    geography and its related terms

    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
    berg
    -0.09
    tá
    -0.09
    /generated
    -0.09
     дело
    -0.09
    è¯Ŀè¯Ń
    -0.09
    æĺĻ
    -0.09
    داÙħ
    -0.08
    å¼Ĭ端
    -0.08
    icable
    -0.08
    å·¥ä½ľæķĪçİĩ
    -0.08
    POSITIVE LOGITS
    undi
    0.11
    ALLY
    0.10
    /ge
    0.10
    /top
    0.10
    \Eloquent
    0.09
    ìłģ
    0.09
    ially
    0.09
    pping
    0.09
    gia
    0.09
    çķĪ
    0.09
    Activations Density 0.021%

    No Known Activations