© 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. 30272
    Prev
    Next
    INDEX
    Explanations

    .hpp or at followed by files

    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
    alled
    -0.11
    êt
    -0.10
    hop
    -0.10
    istance
    -0.10
    horse
    -0.10
    .workflow
    -0.10
    imir
    -0.09
    leston
    -0.09
    mitt
    -0.09
    inson
    -0.09
    POSITIVE LOGITS
    uous
    0.17
    rious
    0.12
    ive
    0.11
    a
    0.10
    rix
    0.10
    uary
    0.10
    rias
    0.09
     remar
    0.09
    resh
    0.09
     Twig
    0.09
    Activations Density 0.001%

    No Known Activations