© 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. 88859
    Prev
    Next
    INDEX
    Explanations

    references followed by section titles

    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
     Fon
    -0.10
     harbour
    -0.09
     cos
    -0.09
     WM
    -0.08
     Hill
    -0.08
     Kod
    -0.08
    iera
    -0.08
    /Application
    -0.08
     boil
    -0.08
     belly
    -0.08
    POSITIVE LOGITS
     Netz
    0.09
     mankind
    0.09
     Approval
    0.09
     Cary
    0.09
    ``↵
    0.09
    enet
    0.08
     Blocked
    0.08
    hs
    0.08
     brows
    0.08
     spirits
    0.08
    Activations Density 0.004%

    No Known Activations