© 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. 46691
    Prev
    Next
    INDEX
    Explanations

    Redistributions of source code

    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
     jab
    -0.11
    lap
    -0.11
     Wheeler
    -0.09
     penny
    -0.09
    hind
    -0.08
    excel
    -0.08
    ombo
    -0.08
     kappa
    -0.08
    hen
    -0.08
     appet
    -0.08
    POSITIVE LOGITS
     situ
    0.10
     underworld
    0.10
     searchable
    0.09
     pros
    0.08
     slick
    0.08
    Locale
    0.08
    /detail
    0.08
     Prov
    0.08
     navegador
    0.08
     partisan
    0.08
    Activations Density 0.002%

    No Known Activations