© 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. 22424
    Prev
    Next
    INDEX
    Explanations

    danish places and names

    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
    åĨ¶çĤ¼
    -0.09
     Hoffman
    -0.09
    ä¾ij
    -0.08
    大åĶIJ
    -0.08
    à°
    -0.08
    anj
    -0.08
    è±³
    -0.08
    ENDER
    -0.08
    itch
    -0.08
    ada
    -0.08
    POSITIVE LOGITS
    丹麦
    0.17
     Danish
    0.17
     Copenhagen
    0.17
    æ²³åįĹçľģ
    0.16
    æ²³åįĹ
    0.15
     Denmark
    0.15
    å¼Ģå°ģ
    0.13
    豫
    0.12
    strup
    0.12
     Nielsen
    0.12
    Activations Density 0.160%

    No Known Activations