© 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. 5490
    Prev
    Next
    INDEX
    Explanations

    fortunately followed by circumstance or situation

    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
    -0.13
    izable
    -0.12
    isable
    -0.11
    ento
    -0.10
    arus
    -0.10
    gable
    -0.10
    pus
    -0.10
    bian
    -0.10
    actable
    -0.10
    achuset
    -0.10
    POSITIVE LOGITS
     circumstance
    0.13
     circumstances
    0.12
    /un
    0.11
     (?)
    0.11
    ALLY
    0.11
    ely
    0.10
    ally
    0.10
    -looking
    0.10
    emente
    0.10
    aly
    0.09
    Activations Density 0.017%

    No Known Activations