© 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. 91977
    Prev
    Next
    INDEX
    Explanations

    circumstances and 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
     moderately
    -0.10
     subtly
    -0.10
    asser
    -0.09
    tempt
    -0.09
    nÄħ
    -0.09
     prova
    -0.09
     relativ
    -0.09
     loosely
    -0.09
     wandered
    -0.09
    rema
    -0.09
    POSITIVE LOGITS
     circumstances
    0.42
     circumstance
    0.33
     contexts
    0.24
     context
    0.24
     conditions
    0.24
    conditions
    0.20
     Context
    0.19
     Conditions
    0.19
     under
    0.18
    context
    0.18
    Activations Density 0.087%

    No Known Activations