© 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. 7397
    Prev
    Next
    INDEX
    Explanations

    date or lists

    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
     sang
    -0.08
     lyrics
    -0.08
     chore
    -0.08
     posts
    -0.08
    ย
    -0.07
     stati
    -0.07
     poste
    -0.07
     patron
    -0.07
    fw
    -0.07
     poem
    -0.07
    POSITIVE LOGITS
     NIC
    0.11
     Organisation
    0.10
    subclass
    0.10
     specialised
    0.10
    aine
    0.10
     teg
    0.10
    storybook
    0.10
    PRINT
    0.10
     defence
    0.10
     TICK
    0.10
    Activations Density 0.002%

    No Known Activations