© 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. 5189
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
     Timothy
    -0.10
     mechanics
    -0.10
     jb
    -0.10
    nte
    -0.10
     Tam
    -0.09
     Rene
    -0.09
     laut
    -0.09
    erah
    -0.09
     Chuck
    -0.09
     tent
    -0.09
    POSITIVE LOGITS
    zug
    0.09
     Mills
    0.09
     sap
    0.09
    sup
    0.09
    Oregon
    0.09
     Inbox
    0.08
    alem
    0.08
    MR
    0.08
     notch
    0.08
    jure
    0.08
    Activations Density 0.001%

    No Known Activations