© 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. 116381
    Prev
    Next
    INDEX
    Explanations

    website, action, online, apartment, games, real estate

    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
    would
    -0.12
    emann
    -0.12
    ican
    -0.11
     would
    -0.11
     Spir
    -0.10
    åĬ¨çĶŁæĪIJ
    -0.10
    ãĤī
    -0.10
    Thrown
    -0.10
    hic
    -0.10
    rw
    -0.10
    POSITIVE LOGITS
     nowadays
    0.13
     chances
    0.12
     inevitably
    0.11
     ideally
    0.11
     normally
    0.10
    ,it
    0.10
     invariably
    0.10
     unavoid
    0.10
     it
    0.09
     does
    0.09
    Activations Density 0.212%

    No Known Activations