© 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. 58925
    Prev
    Next
    INDEX
    Explanations

    police actions and statements

    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
     Gest
    -0.09
    .ErrorCode
    -0.09
    æĪij们éĥ½
    -0.09
    §
    -0.09
    éķ¿éķ¿çļĦ
    -0.09
    ÑĩаÑĤ
    -0.09
    åŁİå¸Ĥ群
    -0.09
    ned
    -0.09
    uez
    -0.08
     Ñģог
    -0.08
    POSITIVE LOGITS
    лав
    0.09
     readonly
    0.09
     hsv
    0.08
    å¸ĥ
    0.08
    çī¹åĪ«å£°æĺİ
    0.08
    峪
    0.08
    漪
    0.08
    NEWS
    0.07
    anya
    0.07
     sealed
    0.07
    Activations Density 0.014%

    No Known Activations