© 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. 31400
    Prev
    Next
    INDEX
    Explanations

    location or direction modifiers

    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
     upfront
    -0.13
     frontline
    -0.13
     interior
    -0.12
     upstream
    -0.12
     backstage
    -0.12
     interiors
    -0.12
     onsite
    -0.11
     Doll
    -0.11
     internally
    -0.11
     frontend
    -0.11
    POSITIVE LOGITS
    /up
    0.09
    /right
    0.09
    /down
    0.08
    /back
    0.08
    stro
    0.08
    imore
    0.08
    /top
    0.07
    /left
    0.07
    beck
    0.07
     bal
    0.07
    Activations Density 0.870%

    No Known Activations