© 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. 114394
    Prev
    Next
    INDEX
    Explanations

    dem- followed by suffixes

    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
    hos
    -0.09
     greed
    -0.09
     prune
    -0.09
     lub
    -0.09
    Christmas
    -0.08
     coarse
    -0.08
    (push
    -0.08
    ма
    -0.08
    Gre
    -0.08
    prm
    -0.08
    POSITIVE LOGITS
    s
    0.14
    yth
    0.10
     wedge
    0.10
    angu
    0.10
    ure
    0.10
     shy
    0.10
     arc
    0.09
     dem
    0.09
    ece
    0.09
    e
    0.09
    Activations Density 0.003%

    No Known Activations