© 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. 31811
    Prev
    Next
    INDEX
    Explanations

    crime and legal proceedings

    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
    urch
    -0.09
    åĪ»
    -0.09
    诸å¦Ĥ
    -0.08
    è¤ļ
    -0.08
    sett
    -0.08
    åħ¥éĢī
    -0.08
    enge
    -0.08
    汶å·Ŀ
    -0.08
    åIJİåı°
    -0.08
    êµ°
    -0.08
    POSITIVE LOGITS
    éĺħ读åħ¨æĸĩ
    0.11
     quad
    0.11
     Drag
    0.09
    ATAB
    0.09
    æĢĢ
    0.09
    éĵĴ
    0.08
    å¹´é¾Ħ
    0.08
    ä½ıåľ¨
    0.08
    äºİæĺ¯æĪij
    0.08
    ICS
    0.08
    Activations Density 0.061%

    No Known Activations