© 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. 91416
    Prev
    Next
    INDEX
    Explanations

    Sus, Contr, Qual, Eff, Trou, Crit, Comb, Cons, Rec

    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
    ellig
    -0.09
    emes
    -0.08
    tam
    -0.08
    hipster
    -0.08
     Lone
    -0.08
    breadcrumb
    -0.08
    ocol
    -0.08
    mime
    -0.08
     Inches
    -0.08
     lone
    -0.08
    POSITIVE LOGITS
     bele
    0.10
    пÑĢав
    0.10
     McConnell
    0.10
    sburg
    0.10
    été
    0.09
     Pad
    0.09
    ingham
    0.09
    gp
    0.09
     troubled
    0.08
    aleb
    0.08
    Activations Density 0.417%

    No Known Activations