© 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. 31613
    Prev
    Next
    INDEX
    Explanations

    amounts and providers

    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
    ording
    -0.11
    rag
    -0.10
    orge
    -0.10
     ruthless
    -0.10
    834
    -0.10
     rear
    -0.10
    vor
    -0.10
    inite
    -0.10
     provisions
    -0.10
    .hr
    -0.10
    POSITIVE LOGITS
    mpi
    0.09
    stakes
    0.08
    miss
    0.08
    SSI
    0.08
     Chili
    0.08
     Bonnie
    0.07
     Marshal
    0.07
    elib
    0.07
    ystal
    0.07
     stakes
    0.07
    Activations Density 0.001%

    No Known Activations