© 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. 27096
    Prev
    Next
    INDEX
    Explanations

    B-type, C-type, P450

    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
     retains
    -0.10
    ypad
    -0.10
    ycastle
    -0.10
    hold
    -0.10
     Lad
    -0.10
     nack
    -0.10
     indeb
    -0.10
    bond
    -0.09
    holds
    -0.09
     digs
    -0.09
    POSITIVE LOGITS
    upo
    0.12
    amage
    0.11
     ydk
    0.08
     twin
    0.08
    ankan
    0.08
    /Resources
    0.08
    operators
    0.08
    IRT
    0.08
    eng
    0.07
     elder
    0.07
    Activations Density 0.033%

    No Known Activations