© 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. 91216
    Prev
    Next
    INDEX
    Explanations

    first, last, final, second, eight

    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
    dge
    -0.11
    UES
    -0.10
    arent
    -0.10
     TBD
    -0.10
     generations
    -0.10
    âĨĵ
    -0.10
    ila
    -0.09
    acht
    -0.09
    ues
    -0.09
    CHAT
    -0.09
    POSITIVE LOGITS
     daily
    0.12
    daily
    0.10
     Thornton
    0.09
    uida
    0.09
     monthly
    0.09
     annual
    0.09
    _daily
    0.09
    ANGER
    0.09
     stop
    0.09
     duty
    0.09
    Activations Density 0.159%

    No Known Activations