© 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. 34039
    Prev
    Next
    INDEX
    Explanations

    Ukraine related topics

    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
    æ³īå·ŀ
    -0.10
    æĪijåıijçİ°
    -0.09
    è¡ĮæĶ¿æī§æ³ķ
    -0.09
    ä¸ŃåĽ½å¸Ĥåľº
    -0.09
    chter
    -0.09
    .au
    -0.09
    qrt
    -0.09
    Ĥ¬
    -0.09
     воÑĤ
    -0.08
    ãģĭãģĭãĤĭ
    -0.08
    POSITIVE LOGITS
    enko
    0.11
    åŁºè¾ħ
    0.11
    -Russian
    0.10
    æ½¼
    0.10
    aise
    0.10
    åĬ²
    0.09
    cio
    0.09
     Donetsk
    0.09
    è¾Ļ
    0.09
     steer
    0.08
    Activations Density 0.029%

    No Known Activations