© 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. 112306
    Prev
    Next
    INDEX
    Explanations

    agreement provided

    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
    gle
    -0.10
     scri
    -0.09
    .setAuto
    -0.09
    itty
    -0.09
    antar
    -0.09
     Scha
    -0.09
     shadow
    -0.09
    |-
    -0.09
     dormant
    -0.09
    loo
    -0.09
    POSITIVE LOGITS
    anos
    0.09
    anus
    0.09
     spont
    0.09
     Faces
    0.09
    ici
    0.09
     deliveries
    0.08
     unpredict
    0.08
     illegally
    0.08
    /boot
    0.08
     decay
    0.08
    Activations Density 0.007%

    No Known Activations