© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50838
    Prev
    Next
    INDEX
    Explanations

    military units, locations, and equipment

    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
    oldt
    -0.10
    uyá»ĩn
    -0.09
    arming
    -0.09
    åį±
    -0.09
     Fleming
    -0.09
    ãģ¥
    -0.09
    .pet
    -0.08
    benh
    -0.08
    _MPI
    -0.08
    çĻ»å±±
    -0.08
    POSITIVE LOGITS
    éªijåħµ
    0.10
    å¢ĥåĨħ
    0.10
    è¿ľç¦»
    0.09
     Ire
    0.09
     scor
    0.09
    é¢Ĩçķ¥
    0.09
    ä¸įåľ¨ä¹İ
    0.09
    éªļæī°
    0.09
    çĦ¼
    0.08
     burned
    0.08
    Activations Density 0.037%

    No Known Activations