© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6151
    Prev
    Next
    INDEX
    Explanations

    attorney’s office

    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
    Negative Logits
    æĥļ
    -0.08
    æİĪ课
    -0.08
    å®ŀåľ¨
    -0.08
    ูล
    -0.08
     ÑĢегиÑģÑĤ
    -0.08
     tilt
    -0.08
    ile
    -0.08
    edia
    -0.08
     Duncan
    -0.08
    æĦŁæŁĵèĢħ
    -0.08
    POSITIVE LOGITS
    æĥłæ°ij
    0.09
    派人
    0.09
    è§Ĥæij©
    0.09
    iams
    0.09
    æį¶
    0.09
    æ´¾åĩº
    0.09
    é¾Ľ
    0.08
    æİĮæı¡äºĨ
    0.08
     далÑĮн
    0.08
    chner
    0.08
    Activations Density 0.012%

    No Known Activations