© 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. 22695
    Prev
    Next
    INDEX
    Explanations

    combat operations and related activities

    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
    -0.11
     воÑĤ
    -0.10
    ings
    -0.09
    grams
    -0.09
    creen
    -0.09
    æĿī
    -0.09
    burn
    -0.08
    ificance
    -0.08
    -up
    -0.08
    ICES
    -0.08
    POSITIVE LOGITS
    -ready
    0.13
    ting
    0.12
    ant
    0.11
    ï¸ı
    0.10
    ï¸
    0.10
    åĵ¡
    0.10
    ted
    0.09
    Çİ
    0.09
     fours
    0.09
    娱
    0.09
    Activations Density 0.011%

    No Known Activations