© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 3632
    Prev
    Next
    INDEX
    Explanations

    black market, illegal cash sales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
    plib
    -0.10
     Ret
    -0.10
     retr
    -0.10
     pam
    -0.09
     boredom
    -0.09
     distracted
    -0.09
     modest
    -0.09
     retention
    -0.09
    baru
    -0.09
     sip
    -0.09
    POSITIVE LOGITS
     illegal
    0.45
     illegally
    0.43
     Illegal
    0.38
     illicit
    0.35
     clandest
    0.34
     unofficial
    0.34
     informal
    0.33
     illeg
    0.32
    illegal
    0.32
     underground
    0.31
    Activations Density 0.121%

    No Known Activations