© 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. 33534
    Prev
    Next
    INDEX
    Explanations

    ice and cold

    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
    rev
    -0.12
    tit
    -0.12
    tion
    -0.11
    ional
    -0.10
    istas
    -0.10
    iones
    -0.10
     Sant
    -0.10
    /Foundation
    -0.10
    /store
    -0.10
    ión
    -0.10
    POSITIVE LOGITS
    berg
    0.11
    y
    0.11
    breaker
    0.11
     cold
    0.11
    iness
    0.11
    -hearted
    0.10
     Cold
    0.10
    cold
    0.10
    Cold
    0.10
    ber
    0.10
    Activations Density 0.019%

    No Known Activations