© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 88108
    Prev
    Next
    INDEX
    Explanations

    how to ask questions

    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
     unfortunately
    -0.10
     fortunately
    -0.10
     respir
    -0.10
     almost
    -0.09
     oddly
    -0.09
     forty
    -0.09
     countless
    -0.09
     Probably
    -0.09
     Unfortunately
    -0.08
     Mou
    -0.08
    POSITIVE LOGITS
    /if
    0.16
    /how
    0.15
    /or
    0.13
    /do
    0.13
    "?↵↵
    0.13
     pls
    0.13
     realistically
    0.12
     yourselves
    0.12
     generally
    0.12
    /
    0.12
    Activations Density 2.585%

    No Known Activations