© 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. 89242
    Prev
    Next
    INDEX
    Explanations

    code testing and logging constructs

    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
    /or
    -0.09
    opus
    -0.07
    Lang
    -0.07
    nas
    -0.07
    oulos
    -0.07
    ¼
    -0.07
    atter
    -0.07
    /of
    -0.07
     Matter
    -0.07
     NAS
    -0.07
    POSITIVE LOGITS
    /gtest
    0.10
    iquement
    0.08
    /comment
    0.08
     promin
    0.08
     pom
    0.08
     embargo
    0.08
     nack
    0.07
    ParseException
    0.07
    Fcn
    0.07
    igte
    0.07
    Activations Density 2.442%

    No Known Activations