© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5340
    Prev
    Next
    INDEX
    Explanations

    form, json, server, county

    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
     Prest
    -0.08
    -indent
    -0.08
     Spir
    -0.07
    thy
    -0.07
     Gast
    -0.07
     Royal
    -0.07
     Kov
    -0.07
    à¥į
    -0.07
     Myst
    -0.07
    ég
    -0.07
    POSITIVE LOGITS
    iona
    0.10
    /Open
    0.10
    actices
    0.09
    /common
    0.09
    nings
    0.09
     Nico
    0.09
    ionale
    0.09
    @student
    0.09
     Mitar
    0.08
    /big
    0.08
    Activations Density 2.206%

    No Known Activations