© 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. 88966
    Prev
    Next
    INDEX
    Explanations

    molecular science

    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
     lust
    -0.11
    atter
    -0.11
    irst
    -0.10
     Ble
    -0.10
    ivi
    -0.10
    ild
    -0.10
     Essence
    -0.09
    slots
    -0.09
    tro
    -0.09
    apon
    -0.09
    POSITIVE LOGITS
    ation
    0.14
     harass
    0.12
    pra
    0.11
     Barcl
    0.10
    ATION
    0.10
     innoc
    0.10
     survivors
    0.10
    /man
    0.09
    ión
    0.09
    hiba
    0.09
    Activations Density 0.013%

    No Known Activations