© 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. 48713
    Prev
    Next
    INDEX
    Explanations

    positional prepositions

    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
     walls
    -0.11
     Walls
    -0.11
     ME
    -0.10
    yles
    -0.09
     ment
    -0.09
    oso
    -0.09
     Crimson
    -0.09
    singleton
    -0.09
     Wall
    -0.08
     Dun
    -0.08
    POSITIVE LOGITS
    neath
    0.12
     description
    0.10
     descriptions
    0.10
     numer
    0.09
     listings
    0.09
    OLDER
    0.09
    words
    0.09
     title
    0.09
     cach
    0.09
     name
    0.09
    Activations Density 0.196%

    No Known Activations