© 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. 18556
    Prev
    Next
    INDEX
    Explanations

    like button

    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
     Burl
    -0.10
     myst
    -0.09
    uate
    -0.08
     McGu
    -0.08
     Middleton
    -0.08
    eno
    -0.08
     shaken
    -0.08
     nog
    -0.08
    .parsers
    -0.08
    _IPV
    -0.07
    POSITIVE LOGITS
    RK
    0.10
    Ob
    0.10
     Tango
    0.09
    dit
    0.09
     Ob
    0.09
    escaping
    0.09
    hiba
    0.09
    /thread
    0.09
    Ok
    0.09
    slick
    0.09
    Activations Density 0.002%

    No Known Activations