© 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. 90685
    Prev
    Next
    INDEX
    Explanations

    atmosphere and atmospheric conditions

    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
    ings
    -0.10
    erva
    -0.09
    grounds
    -0.09
    ific
    -0.09
    tree
    -0.09
    tober
    -0.09
    mont
    -0.08
     polished
    -0.08
    outs
    -0.08
    odia
    -0.08
    POSITIVE LOGITS
    pheric
    0.13
    pheres
    0.12
    -pressure
    0.12
    phere
    0.12
    eus
    0.11
    /ion
    0.11
    aic
    0.11
    /environment
    0.11
     surrounding
    0.11
    ocre
    0.10
    Activations Density 0.025%

    No Known Activations