© 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. 33877
    Prev
    Next
    INDEX
    Explanations

    rs, numbers, dates

    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
    .mj
    -0.12
     PERF
    -0.12
     blat
    -0.11
     Jays
    -0.11
     underside
    -0.11
    isContained
    -0.11
     bdsm
    -0.11
     spanking
    -0.11
     monstr
    -0.11
    deaux
    -0.11
    POSITIVE LOGITS
    %C
    0.06
    !(:
    0.06
    gcc
    0.06
    OTES
    0.05
    âĢİ
    0.05
     linger
    0.05
    &amp
    0.05
    ب
    0.05
     ============================================================================↵
    0.05
    gw
    0.05
    Activations Density 1.627%

    No Known Activations