© 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. 2793
    Prev
    Next
    INDEX
    Explanations

    military bases and sites

    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
    ä¸ĢèĤ¡
    -0.09
    åĩºéŨ
    -0.09
    uckle
    -0.09
    è¿Ļéĥ¨åĪĨ
    -0.08
    æĪĺåľº
    -0.08
    æ²ī浸
    -0.08
    âĸ¡
    -0.08
     ÑĢÑĭн
    -0.08
    楼å±Ĥ
    -0.08
    éħļ
    -0.08
    POSITIVE LOGITS
    åĨħ马
    0.10
    ä¸ĩåIJį
    0.09
    æĸ¹åľĨ
    0.09
    大éŨ
    0.09
    ç¬ij声
    0.09
    æ·ĸ
    0.09
    åĩłåįĥ
    0.09
    ynth
    0.08
    æħĿ
    0.08
    éĻĦè¿ijçļĦ
    0.08
    Activations Density 0.030%

    No Known Activations