© 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. 48173
    Prev
    Next
    INDEX
    Explanations

    emergency preparedness and defense

    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
     ÑĢожд
    -0.10
    itti
    -0.10
    åĢ¡
    -0.10
    æį§
    -0.10
    _REFERER
    -0.09
    æīĺ
    -0.09
    ç´¢åıĸ
    -0.09
    ouns
    -0.09
    Exclusive
    -0.09
    /ros
    -0.09
    POSITIVE LOGITS
    éĺ²ç©º
    0.14
    éģ¿
    0.11
    åħ¨æ°ij
    0.10
    éĺ²
    0.10
    æ¼Ķç»ĥ
    0.10
    åºĶæĢ¥
    0.10
    uclear
    0.10
     wartime
    0.09
    以éĺ²
    0.09
    æĪ·å¤ĸ
    0.09
    Activations Density 0.088%

    No Known Activations