© 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. 56865
    Prev
    Next
    INDEX
    Explanations

    police officers and law enforcement

    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
    èĥĮåıĽ
    -0.10
    éĴº
    -0.09
    è§ĴèIJ½
    -0.09
    å´´
    -0.09
    åĽ¾ä¸º
    -0.09
    yme
    -0.09
    uta
    -0.09
    è¸ı
    -0.09
    æīĵå¾Ĺ
    -0.09
    <<<
    -0.09
    POSITIVE LOGITS
    rens
    0.10
    spm
    0.08
    oz
    0.08
    çĢĽ
    0.08
    é¢Ĥ
    0.08
     rug
    0.08
    æľºåĬ¨è½¦
    0.08
     renew
    0.08
    éĿĸ
    0.08
    çĮľæĥ³
    0.08
    Activations Density 0.107%

    No Known Activations