© 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. 50006
    Prev
    Next
    INDEX
    Explanations

    hot 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
     hottest
    -0.15
     hot
    -0.15
     hotter
    -0.15
     heating
    -0.13
     heated
    -0.13
     overhe
    -0.12
     heat
    -0.12
    Hot
    -0.11
     Heat
    -0.11
    heat
    -0.11
    POSITIVE LOGITS
     stiff
    0.13
    jom
    0.10
    ottom
    0.10
     sme
    0.10
    cola
    0.10
    assage
    0.10
    ainen
    0.10
    izontal
    0.10
     Royale
    0.10
    jt
    0.10
    Activations Density 0.028%

    No Known Activations