© 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. 112930
    Prev
    Next
    INDEX
    Explanations

    beach and sand activities

    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
     downstairs
    -0.16
     upstairs
    -0.12
     Pist
    -0.11
     indoors
    -0.11
     passenger
    -0.10
     dorm
    -0.10
     Harbour
    -0.10
    Mono
    -0.10
     decks
    -0.10
     attic
    -0.10
    POSITIVE LOGITS
     sand
    0.21
     sands
    0.18
     Sand
    0.17
     digging
    0.17
    Sand
    0.15
     dig
    0.15
     SAND
    0.15
     sandbox
    0.14
     Dig
    0.14
     surf
    0.13
    Activations Density 0.112%

    No Known Activations