© 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. 7380
    Prev
    Next
    INDEX
    Explanations

    shore or shores

    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
     forks
    -0.11
    aths
    -0.10
    gew
    -0.10
    /errors
    -0.10
     skies
    -0.10
    osate
    -0.10
    gie
    -0.10
    plier
    -0.10
    coe
    -0.10
    ron
    -0.10
    POSITIVE LOGITS
    lines
    0.18
    line
    0.17
    -line
    0.14
     line
    0.13
    side
    0.12
    birds
    0.12
    -side
    0.12
    /cloud
    0.10
    LINE
    0.10
    break
    0.10
    Activations Density 0.027%

    No Known Activations