© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20315
    Prev
    Next
    INDEX
    Explanations

    place names ending in ville or Springs

    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
    å¾Īæĥ³
    -0.10
    åĽļ
    -0.09
    æ¯ĭ
    -0.09
    淹没
    -0.09
     Juda
    -0.09
     Gates
    -0.09
    峪
    -0.08
    ç«łç¨ĭ
    -0.08
    ÑĤив
    -0.08
    åijĨ
    -0.08
    POSITIVE LOGITS
    飾
    0.09
    æľ¬åĽ½
    0.09
    kie
    0.09
    翳
    0.08
    è¹Ļ
    0.08
    æºŁ
    0.08
    emodel
    0.08
    Bur
    0.08
    /place
    0.08
    åĸĢ
    0.08
    Activations Density 0.026%

    No Known Activations