© 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. 112080
    Prev
    Next
    INDEX
    Explanations

    pent words

    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
    erts
    -0.10
    bx
    -0.09
     decent
    -0.08
     Tubes
    -0.08
     SOS
    -0.08
    orgen
    -0.08
    aan
    -0.08
    onne
    -0.08
    azu
    -0.08
     speculative
    -0.08
    POSITIVE LOGITS
     pent
    0.19
     Pent
    0.16
    -up
    0.14
    pent
    0.14
    ted
    0.11
     Cout
    0.10
     up
    0.10
     Unicorn
    0.10
    -Up
    0.10
    imenti
    0.10
    Activations Density 0.005%

    No Known Activations