© 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. 34478
    Prev
    Next
    INDEX
    Explanations

    military recruitment and service

    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
    串
    -0.13
    串èģĶ
    -0.10
    éĶ²
    -0.10
    æĶ»åħ³
    -0.09
    对æīĭ
    -0.08
    mie
    -0.08
    çIJ´
    -0.08
    åıĭè°Ĭ
    -0.08
    缼ä¼ļ
    -0.08
    çĭ¬åħ·
    -0.08
    POSITIVE LOGITS
    æĭĽåĭŁ
    0.16
    æľįå½¹
    0.13
    æĬ¥åIJį
    0.12
     Recruitment
    0.10
     recru
    0.10
    åĬ¨åijĺ
    0.10
     volunte
    0.10
    åı¬åĶ¤
    0.10
    å¿ĹæĦ¿èĢħ
    0.10
    èĩªæĦ¿
    0.10
    Activations Density 0.106%

    No Known Activations