© 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. 91818
    Prev
    Next
    INDEX
    Explanations

    error messages for attributes, pages, or types

    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
     stuck
    -0.09
     spared
    -0.09
    Started
    -0.09
    anon
    -0.09
    uras
    -0.09
    mant
    -0.08
     Pey
    -0.08
     overloaded
    -0.08
    handled
    -0.08
     stranded
    -0.08
    POSITIVE LOGITS
     requested
    0.12
     pretended
    0.11
    egra
    0.10
     Bust
    0.09
    ucer
    0.09
     Franken
    0.09
    oret
    0.09
    adar
    0.09
    -request
    0.09
    ind
    0.08
    Activations Density 0.174%

    No Known Activations