© 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. 32090
    Prev
    Next
    INDEX
    Explanations

    law enforcement and government agencies

    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
    èµIJ
    -0.08
    涵
    -0.08
    ucks
    -0.08
    ervo
    -0.08
    ils
    -0.07
    å¡«
    -0.07
    roups
    -0.07
    ç²Ĺ
    -0.07
    _lens
    -0.07
    criptors
    -0.07
    POSITIVE LOGITS
    ä½ľèĢħæľ¬äºº
    0.12
    åĪ«çļĦ
    0.11
    åħ¶å®ĥ
    0.11
    /or
    0.10
    åħ¶ä»ĸçļĦ
    0.10
    çĽij管éĥ¨éŨ
    0.09
    æĽ´éĩįè¦ģçļĦ
    0.09
    å½ĵåľ°æĶ¿åºľ
    0.09
    æĽ´éĩįè¦ģ
    0.09
     дÑĢÑĥгие
    0.09
    Activations Density 0.218%

    No Known Activations