© 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. 88413
    Prev
    Next
    INDEX
    Explanations

    cold, colder, chilly, frosty

    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
    aca
    -0.11
     Carm
    -0.09
     pent
    -0.09
    å¯Ĩ
    -0.08
     class
    -0.08
     Sandy
    -0.08
     *>
    -0.08
     affirmative
    -0.08
    ycz
    -0.08
    andel
    -0.08
    POSITIVE LOGITS
     chilly
    0.18
     colder
    0.18
    cold
    0.17
     cold
    0.17
    Cold
    0.15
     Cold
    0.14
     frost
    0.14
     chilled
    0.13
     winters
    0.12
     âĿ
    0.12
    Activations Density 0.094%

    No Known Activations