© 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. 26981
    Prev
    Next
    INDEX
    Explanations

    things pouring in or accumulating

    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
    oger
    -0.08
     Burl
    -0.08
     partially
    -0.08
     Rec
    -0.07
     peripherals
    -0.07
    gra
    -0.07
    net
    -0.07
    ond
    -0.07
     Prim
    -0.07
     scav
    -0.07
    POSITIVE LOGITS
     pouring
    0.15
     flowed
    0.15
     piled
    0.14
    akk
    0.14
     pile
    0.13
     pours
    0.13
     poured
    0.13
     piles
    0.13
     plentiful
    0.13
     accumulating
    0.13
    Activations Density 0.080%

    No Known Activations