© 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. 48205
    Prev
    Next
    INDEX
    Explanations

    military ranks and titles

    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
    ç¥ĸåĽ½
    -0.09
    onte
    -0.09
    åľŁ
    -0.09
    åĩ¿
    -0.08
    çķĻå®Ī
    -0.08
    æĻ¨
    -0.08
    гаÑĢ
    -0.08
    èĬľ
    -0.08
    èݪ
    -0.08
    èįĴ
    -0.08
    POSITIVE LOGITS
    俸
    0.12
    æıIJæĭĶ
    0.11
    档次
    0.10
    è¡Ķ
    0.10
    éħ¬
    0.10
    å¹´èĸª
    0.10
     Mansion
    0.10
    æİĴåIJį第ä¸Ģ
    0.10
    çªł
    0.09
    æĻĭåįĩ
    0.09
    Activations Density 0.044%

    No Known Activations