© 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. 26741
    Prev
    Next
    INDEX
    Explanations

    pr- followed by names or related words

    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
     muster
    -0.11
    Ĺı
    -0.11
    emente
    -0.10
    ourg
    -0.10
    ibia
    -0.09
    uster
    -0.09
     Campo
    -0.09
    URT
    -0.09
    ensch
    -0.09
    eea
    -0.09
    POSITIVE LOGITS
    udence
    0.15
    akash
    0.12
    isms
    0.11
    asad
    0.11
    ismatic
    0.10
    /pr
    0.10
    imo
    0.10
    izes
    0.10
    uned
    0.10
    ima
    0.10
    Activations Density 0.043%

    No Known Activations