© 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. 115237
    Prev
    Next
    INDEX
    Explanations

    directly to

    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
     therein
    -0.10
    wan
    -0.09
    onom
    -0.09
    ajes
    -0.09
     omit
    -0.09
     nearby
    -0.09
    ollar
    -0.09
    ajas
    -0.09
    ewan
    -0.09
    kit
    -0.09
    POSITIVE LOGITS
     firstly
    0.10
     enters
    0.10
     directly
    0.10
     revolving
    0.10
    uno
    0.09
     speculation
    0.09
     scoop
    0.09
     squarely
    0.09
     unanimously
    0.09
     locating
    0.09
    Activations Density 0.039%

    No Known Activations