© 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. 115397
    Prev
    Next
    INDEX
    Explanations

    configuration option

    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
    ocs
    -0.11
     surroundings
    -0.11
    zh
    -0.10
     algorithms
    -0.10
     whim
    -0.10
     Algorithms
    -0.10
    clair
    -0.09
     visuals
    -0.09
     intersections
    -0.09
    .easy
    -0.09
    POSITIVE LOGITS
     component
    0.17
     counterpart
    0.16
     option
    0.16
     section
    0.15
     equivalent
    0.12
     mechanism
    0.11
    section
    0.11
     element
    0.11
     capability
    0.11
     version
    0.10
    Activations Density 1.178%

    No Known Activations