© 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. 58233
    Prev
    Next
    INDEX
    Explanations

    aircraft and helicopter units

    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
    èĮ¸
    -0.09
    æµģåIJij
    -0.09
    è¾Ĭ
    -0.09
    æĹ¥äº§
    -0.09
    ansson
    -0.08
    èħ®
    -0.08
    ä¸ĢéĿ¢
    -0.08
    ogens
    -0.08
    港åĮº
    -0.08
    客æĪ·æıIJä¾Ľ
    -0.08
    POSITIVE LOGITS
    é£ŀæľº
    0.13
     aircraft
    0.11
    æľºåŀĭ
    0.11
    æĪĺæľº
    0.10
    icopt
    0.10
     возд
    0.10
    è½½
    0.10
    çīĮ
    0.09
     Aircraft
    0.09
    å¾Ģ
    0.09
    Activations Density 0.079%

    No Known Activations