© 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. 89017
    Prev
    Next
    INDEX
    Explanations

    session attribute

    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
    aland
    -0.09
    etsk
    -0.09
    asl
    -0.08
     Birch
    -0.08
     Desc
    -0.08
     REV
    -0.08
     industri
    -0.08
    Subsystem
    -0.08
     subsidiary
    -0.08
    Vien
    -0.08
    POSITIVE LOGITS
    ``↵
    0.09
    /her
    0.09
     stump
    0.09
    her
    0.08
    stin
    0.08
    ystal
    0.08
     immature
    0.08
     Conan
    0.08
    ster
    0.08
    `]
    0.08
    Activations Density 0.003%

    No Known Activations