© 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. 32849
    Prev
    Next
    INDEX
    Explanations

    Apache License

    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
    userdata
    -0.10
     glued
    -0.10
    tools
    -0.10
    858
    -0.10
    getc
    -0.10
    onte
    -0.10
    homes
    -0.10
     Pee
    -0.10
     Mature
    -0.10
    /commons
    -0.10
    POSITIVE LOGITS
     kettle
    0.10
     Blind
    0.09
     prepar
    0.09
     obsc
    0.08
     warmer
    0.08
     diff
    0.08
     Record
    0.08
     obscene
    0.08
     forgiven
    0.08
     acceptable
    0.08
    Activations Density 0.042%

    No Known Activations