© 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. 7198
    Prev
    Next
    INDEX
    Explanations

    box-sizing or box-shadow

    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
    side
    -0.10
    OLA
    -0.10
    odos
    -0.10
    stile
    -0.09
    ment
    -0.09
    Facade
    -0.09
    .cgi
    -0.09
    oire
    -0.09
    ahi
    -0.09
     Husband
    -0.09
    POSITIVE LOGITS
     shorts
    0.11
    dre
    0.10
    pra
    0.10
    /lab
    0.09
     jaw
    0.08
    aurus
    0.08
     Jaw
    0.08
     brilliant
    0.08
     Shorts
    0.08
     generalized
    0.08
    Activations Density 0.002%

    No Known Activations