© 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. 18405
    Prev
    Next
    INDEX
    Explanations

    character encoding (charset)

    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
     matrimon
    -0.10
     Higgins
    -0.10
     sexual
    -0.09
     harass
    -0.09
     hookers
    -0.09
    Porno
    -0.09
    iez
    -0.09
     BDSM
    -0.09
     sexually
    -0.09
     cedar
    -0.08
    POSITIVE LOGITS
     phenomenal
    0.10
     Simulator
    0.10
     imagin
    0.10
    %^
    0.09
     finest
    0.09
     top
    0.09
     hottest
    0.09
     deported
    0.09
     quarantine
    0.09
     antlr
    0.09
    Activations Density 0.012%

    No Known Activations