© 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. 48404
    Prev
    Next
    INDEX
    Explanations

    seems to indicate likelihood

    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
    nota
    -0.11
    oder
    -0.10
    [Math
    -0.10
    oka
    -0.10
     Yug
    -0.10
    rier
    -0.10
     ect
    -0.10
    !!)↵
    -0.10
     Halo
    -0.10
    /com
    -0.10
    POSITIVE LOGITS
     likely
    0.10
     pretty
    0.09
     Kern
    0.09
     seems
    0.09
     mostly
    0.08
     prima
    0.08
     mainly
    0.08
    pretty
    0.08
     universally
    0.08
    YS
    0.08
    Activations Density 0.144%

    No Known Activations