© 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. 28005
    Prev
    Next
    INDEX
    Explanations

    image description below

    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
     proceeding
    -0.11
     Detailed
    -0.11
     Videos
    -0.10
    .rar
    -0.10
    robe
    -0.10
    adge
    -0.10
    Rich
    -0.10
     videot
    -0.10
    _started
    -0.10
     TSR
    -0.10
    POSITIVE LOGITS
     shows
    0.21
     depicts
    0.18
     showing
    0.18
     above
    0.16
    shows
    0.15
     depicting
    0.15
     illustrates
    0.15
     Shows
    0.15
     represents
    0.14
     representation
    0.14
    Activations Density 0.574%

    No Known Activations