© 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. 17538
    Prev
    Next
    INDEX
    Explanations

    words starting with "Pr"

    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
    house
    -0.11
    emente
    -0.11
    entes
    -0.09
    INGTON
    -0.09
    antry
    -0.08
    dings
    -0.08
    UMENT
    -0.08
     Sight
    -0.08
     surely
    -0.08
    entine
    -0.08
    POSITIVE LOGITS
    /pr
    0.13
    eln
    0.10
    izr
    0.10
     Practical
    0.10
    ivity
    0.10
    -pr
    0.10
     prizes
    0.10
    /Application
    0.10
     Riding
    0.09
    icking
    0.09
    Activations Density 0.013%

    No Known Activations