© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51931
    Prev
    Next
    INDEX
    Explanations

    Finland and Finnish

    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
    èĿİ
    -0.09
    æĻĥ
    -0.09
    çīĤ
    -0.08
    ibase
    -0.08
    TPL
    -0.08
    elli
    -0.08
     Heller
    -0.08
    éĩįçİ°
    -0.08
    IDs
    -0.08
    .Obj
    -0.08
    POSITIVE LOGITS
    èĬ¬åħ°
    0.20
     Helsinki
    0.14
     Finnish
    0.14
     Finland
    0.13
    elsinki
    0.09
    åĪĽä¸ļ
    0.09
    奶奶
    0.09
    æ§Ľ
    0.09
    åį¢
    0.09
    éĹ¾
    0.09
    Activations Density 0.063%

    No Known Activations