© 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. 32834
    Prev
    Next
    INDEX
    Explanations

    finding name, senior, free, or terminal

    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
     Extended
    -0.10
    lav
    -0.10
     ASE
    -0.08
     conver
    -0.08
     cov
    -0.08
     comparison
    -0.07
     Carr
    -0.07
     chart
    -0.07
     Aub
    -0.07
     dich
    -0.07
    POSITIVE LOGITS
    aign
    0.13
     Uploaded
    0.10
    ilden
    0.10
     Facing
    0.10
     Darling
    0.10
     reinc
    0.09
    }elseif
    0.09
     Gates
    0.09
     supermarket
    0.09
     lineage
    0.09
    Activations Density 0.001%

    No Known Activations