© 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. 47666
    Prev
    Next
    INDEX
    Explanations

    breeding, Eagles, messages, devised

    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
    vette
    -0.07
     ler
    -0.06
    ensored
    -0.06
    vit
    -0.06
    acro
    -0.06
     Bai
    -0.06
    igar
    -0.06
     whats
    -0.06
    uncio
    -0.06
    Pel
    -0.05
    POSITIVE LOGITS
     Olson
    0.10
    IFn
    0.10
     Cooke
    0.09
    dap
    0.09
    zin
    0.09
     Gio
    0.09
    SourceType
    0.09
    =@"
    0.09
     lesb
    0.09
    /controllers
    0.09
    Activations Density 1.761%

    No Known Activations