© 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. 16745
    Prev
    Next
    INDEX
    Explanations

    these [noun]

    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
    brtc
    -0.11
    lando
    -0.11
    oger
    -0.11
     reconoc
    -0.11
    olu
    -0.11
    erc
    -0.10
    ↵                    ↵
    -0.10
    UTIL
    -0.10
     cop
    -0.10
    edic
    -0.10
    POSITIVE LOGITS
     types
    0.16
     type
    0.15
     kinds
    0.15
     particular
    0.15
     kind
    0.14
     ones
    0.13
     sorts
    0.12
    types
    0.11
    -type
    0.11
     latter
    0.10
    Activations Density 0.257%

    No Known Activations