© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48692
    Prev
    Next
    INDEX
    Explanations

    arrests, criminal, prosecution

    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
    Not in Any Lists

    No Comments

    Negative Logits
    enko
    -0.09
     Shark
    -0.09
     tent
    -0.09
     Guns
    -0.09
     AVC
    -0.08
     terrorists
    -0.08
     Gun
    -0.08
     schl
    -0.08
     Zar
    -0.08
     reconciliation
    -0.08
    POSITIVE LOGITS
     obsc
    0.23
     prosecutions
    0.22
     sod
    0.21
     prosecuted
    0.17
     prosecution
    0.17
     obscene
    0.16
     criminal
    0.16
     arrests
    0.15
     blasph
    0.15
     lib
    0.14
    Activations Density 0.234%

    No Known Activations