© 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. 8506
    Prev
    Next
    INDEX
    Explanations

    European

    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
    ç¾İæĸ¹
    -0.12
    unks
    -0.09
    çľĭçĶµå½±
    -0.09
    ç²Ĺç³Ļ
    -0.09
    æµ·åĨħå¤ĸ
    -0.09
     sourceMappingURL
    -0.09
    åĽ½åĨħå¤ĸ
    -0.09
    osite
    -0.09
    _SPECIAL
    -0.09
    é¾Ł
    -0.09
    POSITIVE LOGITS
    欧洲
    0.18
     European
    0.16
     europ
    0.15
     Europe
    0.15
     Euro
    0.14
    .eu
    0.14
     europe
    0.13
    European
    0.13
    æ¬§çĽŁ
    0.13
    欧åħĥ
    0.13
    Activations Density 0.155%

    No Known Activations