© 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. 26739
    Prev
    Next
    INDEX
    Explanations

    version numbers and names

    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
     VII
    -0.10
    trad
    -0.09
    .biz
    -0.09
     cum
    -0.09
    history
    -0.08
    /bus
    -0.08
    amic
    -0.08
    ³
    -0.08
    CCA
    -0.08
     XP
    -0.08
    POSITIVE LOGITS
    -era
    0.17
     onwards
    0.16
     era
    0.15
     onward
    0.13
     soundtrack
    0.12
     Prelude
    0.12
     Era
    0.12
    -exclusive
    0.10
     Preview
    0.10
     novel
    0.10
    Activations Density 1.504%

    No Known Activations