© 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. 31105
    Prev
    Next
    INDEX
    Explanations

    volume, MMP, Dig, Collection, Thor

    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
    lash
    -0.09
    eken
    -0.09
     tah
    -0.08
     inplace
    -0.08
     Pere
    -0.08
    uvo
    -0.08
     requisite
    -0.08
    -fi
    -0.08
     tin
    -0.08
    /per
    -0.08
    POSITIVE LOGITS
     %.
    0.10
    ï¼Į并
    0.10
    âĢ¦and
    0.10
    istique
    0.10
     whereas
    0.10
     fray
    0.09
    âĢ¦but
    0.09
     anyhow
    0.08
    ++.
    0.08
    addock
    0.08
    Activations Density 0.530%

    No Known Activations