© 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. 49542
    Prev
    Next
    INDEX
    Explanations

    sharing creations or opinions

    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
    orde
    -0.12
    fad
    -0.12
    azer
    -0.11
    .dex
    -0.11
    /disc
    -0.11
    PRESENT
    -0.10
    /server
    -0.10
    ìŀĦ
    -0.10
     Randolph
    -0.10
     Zur
    -0.10
    POSITIVE LOGITS
     publicly
    0.16
     online
    0.14
     externally
    0.11
     public
    0.10
     anonymously
    0.10
     openly
    0.09
     aloud
    0.09
     aup
    0.09
     commercially
    0.09
     others
    0.09
    Activations Density 0.177%

    No Known Activations